international association forprogramme icdar2009 · continuous support in the secretariat tasks....
TRANSCRIPT
1 ICDAR 2009
Programme at a Glance
26‐29 July, Barcelona, Spain 2
10th International Conference on Document Analysis and Recognition
icdar2009 Barcelona, Spain, 26‐29 July 2009
http://www.icdar2009.org
Sponsored by TC10 (Graphics recognition) and TC11 (Reading systems) of the International Association for Pattern Recognition (IAPR) and the organizations
shown on the opposite page
3 ICDAR 2009
Sponsors ICDAR 2009 is sponsored by TC10 (Graphics Recognition) and TC11 (Reading Systems) of the International Association of Pattern Recognition (IAPR) and by
the following organisations:
26‐29 July, Barcelona, Spain 4
Table of Contents Programme at a Glance ...................................................................................... 1 Sponsors ............................................................................................................. 3 Table of Contents................................................................................................ 4 Welcome from the Conference Chairs ............................................................... 5 Message from the Technical Program Chairs ..................................................... 7 Committees ........................................................................................................ 9 Local Information.............................................................................................. 11 Transportation .................................................................................................. 13 Conference Information ................................................................................... 18 Social Program.................................................................................................. 20 Workshops ........................................................................................................ 23 Tutorials ............................................................................................................ 26 Awards .............................................................................................................. 33 Invited Talks ...................................................................................................... 36 Technical Programme....................................................................................... 43 Phrasebook ....................................................................................................... 75 Conference Statistics ........................................................................................ 77 Notes................................................................................................................. 78
5 ICDAR 2009
Welcome from the Conference Chairs
t is our great pleasure to welcome you to Barcelona and to the Tenth International Conference on Document Analysis and Recognition (ICDAR2009), held at the Universitat Autònoma de Barcelona (UAB), Catalonia, Spain in July 26‐29, 2009.
ICDAR is the main event of the technical committees TC‐10 and TC‐11 within the International Association for Pattern Recognition (IAPR).
Barcelona is the capital of Catalonia. It was founded on the Mediterranean coast, between two rivers, over 2,000 years ago. Since then, it has been the traditional gateway to the Iberian Peninsula. Through it entered Romans, Arabs and Christians, as well as the many diverse cultures, which came to enrich its heritage. The traces of this history and diversity can be followed as you walk through the city; through its Gothic Quarter, built on the Roman ruins; through its art‐nouveau Eixample district, presided over by Gaudí’s exuberant architecture, which at the same time reveals an ordered and rational urban layout. This diversity and harmony are also apparent in the character of the people of Barcelona, who are enterprising and hard‐working, enjoy life and, in particular, have great civic pride and are lovers of culture. In addition to the scientific program, we hope you will spend some time in visiting and enjoying the city.
The volume and quality of technical material submitted to the conference confirm that Document Analysis and Recognition is an active community, both from the scientific and industrial sides, and reinforce ICDAR’s status as one of the flagship Pattern Recognition conferences. ICDAR2009 has a varied and high quality technical program. We have received more than 430 submissions, a record in the history of the conference. Of these, about 20% were accepted as oral and 44% as poster presentations. About a 16% of accepted papers have at least one author from a company, which shows that our research has a strong industrial impact, and the field is rich in industry‐academia pathways. Besides the main conference, ICDAR2009 includes four satellite workshops, four tutorials and nine competitions.
We wish to congratulate Prof. Horst Bunke who received the IAPR/ICDAR Outstanding Achievements Award for his outstanding and continued contributions to research and education in handwriting recognition and document analysis, and services to the community. We also wish to congratulate Dr. Katrin Franke who received the IAPR/ICDAR Young Investigator Award for her outstanding contributions to handwriting analysis and computational forensics.
I
26‐29 July, Barcelona, Spain 6
We would like to thank the many people and institutions who have worked in the different organization tasks. A conference of this magnitude could not be possible without the voluntary and enthusiastic work of tens of people “behind the scenes”. Thanks to the three Program Chairs (Dr. Apostolos Antonacopoulos, Dr. Mohamed Cheriet and Dr. Umapada Pal) for their excellent work and their wise advice on organizing the technical program; the Program Committee and the additional reviewers for their thorough and timely reviewing of the papers; the chairs of the different committees for their valuable cooperation; the industry partners and institutional sponsors for their generous contribution to ICDAR2009, especially valuable given the current economical situation worldwide. We want to especially thank the Local Organizing Committee, the members of the Pattern Recognition and Document Analysis Group of the Computer Vision Center (CVC), and the CVC administrative staff. They have all worked extremely hard on countless and important details of the conference program and social activities. A warm gratitude to Maria Teresa Ibáñez (Ultramar Events) and Meritxell Navarro (APAC‐UAB) for their continuous support in the secretariat tasks. Last but not least, we gratefully acknowledge Dr. Dimosthenis Karatzas, who actively worked with us in the leadership of the ICDAR2009 organization.
We hope that ICDAR2009 will be an exciting technical meeting, and we wish you a very fruitful stay in Barcelona, both scientific and social. We look forward to seeing you all in Barcelona in July 2009.
Josep Lladós General Chair
Ernest Valveny Gemma Sánchez Executive Co‐chairs
7 ICDAR 2009
Message from the Technical Program Chairs
e are delighted to present the program of ICDAR2009. At this 10th edition of ICDAR our community is stronger than ever, as evidenced by the record number of submissions we received. In fact, submission numbers have
been steadily increasing over at least the last ten years, with ICDAR2009 receiving 14% more papers than the previous one (which had broken the previous record).
Overall, 430 papers were submitted from 43 countries from 6 continents (submissions from Antarctica still elude us). In the tradition of past ICDARs we list the breakdown of submissions by continent and the difference from the immediately preceding edition: Africa 25 (+11), Asia 179 (+29), Europe 145 (+15), North America 57 (‐6), South America 22 (+4), Oceania 2 (+0).
We gathered 1286 reviews with the invaluable help of 263 reviewers (including members of the Program and Organising committees as well as additional reviewers). Based on these reviews, 87 papers were accepted for oral presentation. Since this number is relatively fixed (due to the limited number of available presentation slots), the increased number of submissions has resulted in a significant reduction of the oral presentation acceptance rate. It currently stands at 20% bringing ICDAR in line with other premier conferences in related fields. We also accepted 190 papers to be presented as posters based both on reviewers’ recommendations as well as on the fact that, due to their nature, some papers lend themselves better to one‐to‐one discussion.
The main body of oral presentations (21 sessions) is structured into three parallel tracks, while on each day there is a plenary session dedicated to posters. A number of special plenary sessions have also been organised. First, the keynote speech of the recipient of the IAPR/ICDAR Outstanding Achievements Award, Prof Horst Bunke, will open the conference. Second, the technical program includes four keynote talks given by world leading experts in the respective fields to contribute major perspectives from academia, document collection holders and industry. Third, a panel session has been introduced to offer the opportunity for interactive discussion. Finally, a plenary session is set aside for the presentation of the results of the many competitions that were organised in the context of ICDAR, before the closing session where the winners of the various best paper awards will be announced.
We sincerely hope that you will find interesting papers presented during the conference and that the proceedings will also serve as reference, well after
W
26‐29 July, Barcelona, Spain 8
ICDAR2009, for the valuable ideas and the good work produced by our community. A special issue of the International Journal on Document Analysis and Recognition (IJDAR) is also planned after the conference to showcase some of the best papers. For that purpose, top‐ranked papers were selected and their authors invited to prepare a suitably enhanced version of their work for submission to the special issue.
Last but not least, many thanks are due to the program committee members and all additional reviewers for their outstanding and timely work.
We are looking forward to meeting all of you at the 10th ICDAR in the beautiful city of Barcelona!
With warmest wishes,
Apostolos Antonacopoulos Program Chair – Europe/Africa
Mohamed Cheriet
Program Chair – Americas
Umapada Pal Program Chair – Asia/Oceania
9 ICDAR 2009
Committees
General Chair Lladós, Josep (CVC‐UAB, Spain)
Executive co‐Chairs Valveny, Ernest (CVC‐UAB, Spain) Sánchez, Gemma (CVC‐UAB, Spain)
Program Chair (Europe / Africa) Antonacopoulos, Apostolos (University of Salford, UK)
Program Chair (Americas) Cheriet, Mohamed (ETS, Canada)
Program Chair (Asia / Oceania) Pal, Umapada (ISI, India)
ICDAR Advisory Board Antonacopoulos, Apostolos (University of Salford, UK)
Dengel, Andreas (DFKI GmbH, Germany) Liu, Wenyin (City University of Hong Kong, China)
Lopresti, Daniel P. (Lehigh University, USA) Marinai, Simone (University of Florence, Italy)
Workshops Chair Hu, Jianying (IBM TJ Watson Center, USA)
Tutorials Chair Ogier, Jean‐Marc (Université La Rochelle, France)
Competitions Chair Liu, Wenyin (City University of Hong Kong, China)
Publicity Chairs Marinai, Simone (University of Florence, Italy) Kwon, Young‐Bin (Chungang University, Korea)
Oliveira, Luiz Eduardo S. (PUCPR, Brazil)
26‐29 July, Barcelona, Spain 10
Sponsors Chair Sabourin, Robert (ETS, Canada)
Publications Chairs Karatzas, Dimosthenis (CVC, Spain)
Ramos, Oriol (CVC, Spain)
Finance Chair Merino, Maria (CVC, Spain)
TC10 Chair Liu, Wenyin (City University of Hong Kong, China)
TC11 Chair Lopresti, Daniel P. (Lehigh University, USA)
Program Committee Alimi, A.M. (Tunisia) Anquetil, É. (France) Baird, H.S. (USA) Barney Smith, E.H. (USA) Belaid, A. (France) Blostein, D. (Canada) Blumenstein, M. (Australia) Bortolozzi, F. (Brazil) Breuel, T. (Germany) Bui, T.D. (Canada) Bunke, H. (Switzerland) Chaudhuri, B.B. (India) Choisy, C. (France) Chhabra, A. (USA) Coüasnon, B. (France) Dengel, A. (Germany) Ding, X. (China) Doermann, D. (USA) Fairhurst, M. (UK) Fujisawa, H. (Japan)
Gatos, B. (Greece) Govindaraju, V. (USA) Heutte, L. (France) Ho, T.K. (USA) Hull, J.J. (USA) Ingold, R. (Switzerland) Jaeger, S. (USA) Jin, L.‐W. (China) Kim, J.H. (Korea) Kimura, F. (Japan) Kise, K. (Japan) Lam, L. (Canada) Likforman, L. (France) Liu, C. (China) Lopresti, D.P. (USA) Lucas, S. (UK) Manmatha, R. (USA) Märgner, V. (Germany) Nakagawa, M. (Japan) Natarajan, P. (USA)
Nishida, H. (Japan) Paquet, T. (France) Sadri, J. (Canada) Omachi, S. (Japan) Park, J. (Korea) Plamondon, R. (Canada) Sako, H. (Japan) Schomaker, L. (Netherlands) Shimodaira, H. (UK) Sridhar, M. (USA) Srihari, S. (USA) Tabbone, S. (France) Taghva, K. (USA) Tan, C.L. (Singapore) Tombre, K. (France) Uchida, S. (Japan) Viard‐Gaudin, C. (France) Vidal, E. (Spain) Vincent, N. (France) Wakahara, T. (Japan)
11 ICDAR 2009
Local Information
About Barcelona Barcelona is the capital of the autonomous region of Catalonia, at the north‐east corner of Spain. The region is divided in four provinces named after their capitals: Barcelona, Girona, Lleida and Tarragona. The city of Barcelona lies between two rivers, the Llobregat and the Besós, and it is backed by the Collserola hills which rise to a 512m peak at the Tibidabo amusement park. The city grew up as the industrial sweatshop of Spain, though the shunting yards and the seaside warehouses have now gone. Around 4 million people live in Barcelona and its suburbs – about half the population of Catalonia – which makes Barcelona Spain’s second city after Madrid.
Universitat Autónoma de Barcelona The Universitat Autónoma de Barcelona (UAB) is a comparatively young institution, founded in 1968, but in its short history it has moved forward at a rapid pace. It currently has more than 40 thousand registered students and
comprises 54 academic departments and an equally high number of associated institutes and research centres located in three campuses in Barcelona. The Bellaterra campus, the main campus of the UAB and the location of the ICDAR 2009 venue, is situated at the very heart of the greater Barcelona metropolitan area about 20km away from Barcelona city‐centre and next to an important technological park.
26‐29 July, Barcelona, Spain 12
The Conference Venue The conference will take place at the Convention Center “Serhs Hotel Campus” situated in the Bellaterra UAB Campus. The delegates that have chosen to stay in the conference hotel or in the apartments of the “Vila Universitaria” will be within walking distance from the conference venue. The conference venue is well connected to Barcelona city centre while free bus links to the city centre will be provided for the duration of the conference (see next section).
Other Useful Information Currency. The euro (€) is the official currency of the European Union and can be exchanged at banks. The approximate exchange rate to USD is €1 = $1.38. Climate. The local climate is Mediterranean. During the time of the conference, the temperature typically ranges between 25°C and 32°C. Language. In Barcelona, official languages are Catalan and Spanish. People in Barcelona can normally speak English so you should have no problems getting around. Check also the Phrasebook at the end of the booklet. Time Zone. Barcelona Time is in the Central European Time Zone which is 1 hour ahead of Greenwich Mean Time (GMT+1). Electricity. Electric outlets in Barcelona can accommodate European plugs only. Barcelona follows the standard electric current of 220 volts/60 cycles, with two pin plugs. Credit Cards. Shops, hotels and restaurants accept VISA, MasterCard, Diners Club and American Express credit cards, as well as Eurochecks and Eurocards. Telephone. Coins or prepaid cards may be used at any local pay phone. The international access code for Spain is +34. Foreign cellular phones work in Spain. The international prefix to call abroad is 00. In case of medical emergency dial 061, in case of a police emergency 091.
13 ICDAR 2009
Transportation
Arriving in Barcelona Barcelona has a major international airport located 18km from the city centre, with flights coming from Europe, America and the rest of the world. There are also airports in Girona and Reus with bus links to Barcelona while you can also reach Barcelona by boat and by train. The new south terminal (T1) of Barcelona airport was inaugurated in June 2009. Pay attention to which terminal you arrive at, as train links to the city are still only available through the old terminal (T2). There are continuous shuttles running between the two terminal buildings that take about 10 minutes.
From the Airport to Barcelona City Centre By Bus. Buses A1 (to T1) and A2 (to T2) link the airport to “Plaça Catalunya”, the central square of the city. Tickets can be purchased on the bus. Timetable: Departures from Pl. Catalunya every day 5:30 to 00:30. Departures from the airport every day 06:05 to 01:05. Buses run every 7 to 15 minutes. Fares: Single trip: €5 (A1) / €4.25 (A2). Return trip: €8.65 (A1) / €7.30 (A2). More information: http://www.emt‐amb.com/
By Train. Line of the suburban train links the airport with the “Sants Barcelona” train station. The trip takes about 20 minutes. Timetable: Departures From the airport from 06:00 to 23:44. Departures from the Estació de França from 05:20 to 22:42. Trains run every 30 minutes. Fares: The Airport falls within zone 1 of the integrated fare system. Single trip, €1.35; 10‐trip card (T‐10), €7.70. More information: http://www.renfe.com/
26‐29 July, Barcelona, Spain 14
By Taxi. Barcelona’s taxis are yellow and black and display a green light when they are free. You can get a taxi from outside any of the airport terminals. Fares: Approximate rates from the airport on working days (from 07.00 to 21.00): to Plaza España, €14.90; to Plaza Catalunya, €17.20. Approximate rates on Saturdays, holidays and at night (from 21.00 to 07.00): to Plaza España, €17.80; to Plaza Cataluña, €20.60. These rates include the airport supplement. The luggage supplement is 0.90 € per item. The cost payable is as indicated on the meter. Users are advised to request a receipt (see also Phrasebook section). Reservations: +34 933 033 033 More information: http://www.radiotaxi033.com/
From Barcelona City Centre to the UAB Campus Conference Bus. Free bus links between Barcelona city centre and the conference venue will be provided for the duration of ICDAR 2009. The detailed routes are listed below. Timetable:
Day Time From To 18:00 Pl. Catalunya1 Hotel Serhs
Sun 26th After reception2 Hotel Serhs Pl. Catalunya1 8:00 Pl. Catalunya1 Hotel Serhs 9:30 Hotel Serhs Pl. Catalunya1 18:00 Pl. Catalunya1 Hotel Serhs
Mon 27th
19:00 Hotel Serhs Pl. Catalunya1 8:00 Pl. Catalunya1 Hotel Serhs 9:30 Hotel Serhs Pl. Catalunya1 19:00 Hotel Serhs Maremagnum3
Tue 28th
After Banquet4 Maremagnum3 Hotel Serhs 8:00 Pl. Catalunya1 Hotel Serhs 9:30 Hotel Serhs Pl. Catalunya1 18:00 Pl. Catalunya1 Hotel Serhs
Wed 29th
19:00 Hotel Serhs Pl. Catalunya1 1 The buses will stop at the bottom of Pl. Catalunya, in front of “Hard Rock Café”. 2 The buses will start returning to Barcelona when the welcome reception is over. 3 On Tuesday the buses will take the delegates directly to Maremagnum, the Banquet venue. 4 The buses will start the way back when the banquet is over. On the way back all buses will make a stop to Pl. Catalunya for the participants living at the city centre.
15 ICDAR 2009
By Metro. Lines (Pl. Catalunya – Sabadell) and (Pl. Catalunya – Univ. Autònoma) connect the UAB campus to the city centre. The journey time is 30 minutes. The metro stop closest to the conference venue is “Bellaterra”. Timetable: Departures approximately every 10 minutes. Fares: The UAB campus falls within zone 2 of the integrated fare system. Single trip, €2.05; 10‐trip card (T‐10) €15.40. More information: http://www.fgc.net
By Train. Line of the suburban train connects Pl. Catalunya with the UAB campus (“Cerdanyola‐Universitat”). The journey takes approximately 30 minutes. There is a free university UAB shuttle service connecting the main faculties with the RENFE station and the Vila Universitaria. Make sure to take the “red line” bus as “blue line” buses do not stop at Vila Universitaria. Timetable: Departures every 30 minutes. Fares: The UAB campus falls within zone 2 of the integrated fare system. Single trip, €2.05; 10‐trip card (T‐10) €15.40. More information: http://www.renfe.com/
By Bus. The SARBUS service , connects Barcelona (“Fabra i Puig” Station) to the UAB, while there is also a night bus, , that operates between Pl. Catalunya and the UAB campus. The bus journey takes approximately 40 minutes. Timetable: Departures A3, every 30 minutes. Departures N62 from Pl. Catalunya (1:05 to 4:05) every hour. Departures N62 from UAB campus (0:18 to 3:18) every hour. Fares: The UAB campus falls within zone 2 of the integrated fare system. Single trip, €2.05; 10‐trip card (T‐10) €15.40. More information: http://www.sarbus.com/paginas/horarios.php
26‐29 July, Barcelona, Spain 16
By Car. The easiest way to get to the UAB by road is to take the motorway. If coming from the North take AP‐7, direction “Tarragona‐Lleida”, if travelling from the Barcelona or the South, take AP‐7 direction “Girona”. Alternatively from Barcelona you can take C‐58 (Barcelona – Sabadell – Terassa).
Transportation: Airport – UAB Campus Barcelona's el Prat Airport is approximately 30 kilometres from the UAB campus where the Serhs Hotel (conference venue) and the Vila Universitaria apartments are located. Driving from the airport to the UAB campus takes about 25 minutes. Using public transport is also possible, but all routes will take you through the Barcelona city (see previous sections).
Around the UAB Campus Within the UAB Campus and within walking distance from the conference venue, there are shops, restaurants and cash points. Below is a map indicating some of them, as well as the closest metro stations (FGC) and the train station (RENFE).
17 ICDAR 2009
Around the City Centre All the Barcelona conference hotels are located close to Pl. Catalunya. Below is a map of the city centre.
26‐29 July, Barcelona, Spain 18
Conference Information
Conference Sessions: Three function rooms located on the first floor will be used for the conference sessions (“Arnau de Vilanova”, “Lluís Vives I” and “Lluís Vives II”). Posters will be placed at the back of the “Arnau de Vilanova”. Registration Desk: The registration desk is located on the ground floor and will be manned for the duration of the conference. The registration desk will also be open on Sunday 26th (Tutorials day) from 8:30 in the morning, during lunch time and before the welcome reception. On Monday 27th (first day of the conference) the registration desk will open at 8:00.
19 ICDAR 2009
Participants’ Kit: The participants’ kit contains the following items: • Conference bag • This guide • Notebook and Pen • USB‐key electronic proceedings • Tourist information • Banquet invitation
• Certification of attendance • Conference Badge • ICDAR T‐shirt • Printed Proceedings (if ordered) • Free entrance for the CosmoCaixa Science museum
If you have purchased any additional invitations to the conference Banquet they will also be included in your conference bag. Sponsors: The common foyer of “Lluís Vives I” and “Lluís Vives II” will serve as a show room where sponsors will set up demos and distribute information. Lunch: All lunches will take place on the ground floor, in the function room “Martí Franqués”, with the exception of the tutorials day (Sunday 26th), when lunch will be served in the “Sirius Restaurant”. Coffee breaks will take place in the patio of the first floor. Internet Access: Wireless internet access will be available throughout the conference. A limited number of computers will be available in the ground floor next to the registration desk for use by ICDAR participants. If you want to connect your own device please follow the following steps.
1. Connect your device and verify that you have wireless coverage. Select the SSID with name “UAB”. Please, make sure you have selected the “Automatically obtain an IP and DNS address” option in wireless connection properties.
2. Open any Web browser and try to access any Web page. This will automatically open the Welcome page of the UAB portal. Here you can select Anonymous access or personalized access. Select the first option “Guest anonymous access (only http and https on non UAB servers)”.
3. After that, you will be shown the wireless security agreement which you have to accept in order to continue.
4. If all steps are followed correctly, a welcome message will be displayed informing you that you have been successfully connected.
26‐29 July, Barcelona, Spain 20
Social Program
Welcome Reception
Date and Time: Sunday, July 26th, starting at 19:00 Place: “Hotel Serhs Campus”, the conference venue Notes: Conference buses will pick up participants staying at the Barcelona city centre hotels at 18:00 from Pl. Catalunya (outside the “Hard Rock Café”). At the end of the reception the inverse itinerary will be followed.
Conference Banquet
Date and Time: Tuesday, July 28th, starting at 19:00 Place: “Sala Maremagnum”, Port Vell, Barcelona Notes: Conference buses will leave from the “Hotel Serhs Campus” when the sessions of the day finish around 19:00. Before the dinner, we will go on a boat trip around the the Port Vell (Old Harbour). After enjoying the beautiful views of the port and the coast of Barcelona, a reception will be held at the “Sala Maremagnum”, followed by the conference dinner. Please, remember to confirm your participation to the dinner in the registration form. Extra tickets can be purchased online through the conference registration site or on‐site at the registration desk. Early registration is strongly recommended as places are limited!
Post‐conference Tour
Date and Time: Thursday, July 30th, starting at 9:00 Place: Montserrat and Torres Winery Notes: For the day after the conference the organising committee has planned a day‐trip to Montserrat and the Torres Winery. The “serrated mountain” (mont serrat), is a superb setting for Catalonia’s holiest place, the Monastery of Montserrat, which is surrounded by chapels and hermits’ caves. The monastery was first mentioned in the 9th century and in 1409 became independent of Rome. In 1811, when the French attached Catalonia the monastery was destroyed to be rebuilt and repopulated in 1844. Today Benedictine monks live here. We will go to the top of the Montserrat mountain by cable car, hear the “Escolania” (the oldest boys’ music choir in Europe) and enjoy a picnic lunch in the open. We will then continue to the
21 ICDAR 2009
Torres Winery, where a 1h visit will be held. During the visit we will emerge into the wine‐making culture of the area and join a train‐tour among the vineyards and the winery. At the end of the visit there will be a wine tasting session. The cost for this excursion is not included in the conference registration. You can optionally register for this event online or purchase extra tickets from the registration desk. Early registration is strongly recommended as places are limited!
Tours for Accompanying Persons
Tours for accompanying persons will be organised for each day of the conference. You can register for any of these tours through the conference registration Web site or purchase extra tickets from the registration desks. Early registration is strongly recommended. Prices are per person including: Accompanying English speaker guide, local guide, private transport, guided visits, entrance tickets, lunch and taxes, based on 15 people per excursion. Please check upon arrival whether your tour is taking place as some tours require a minimum number of participants. In case a tour is cancelled you will be refunded automatically to the card used for the reservation. Activity: Day‐trip to Girona and Figueras Date: Monday, July 27th Time: Buses will pick up participants from “Hotel Serhs Campus” at 9:00 Price: €106.82 per person Duration: 10 hours Description: The first stop will be the town of Girona, about 1.5h North of Barcelona. Girona is one of the most interesting cities in Spain, with a long history and rich cultural background. Four rivers cross each other in Girona. While in Girona the participants will visit the Cathedral of Santa Maria, and will be taken on a walk around “El Call” (the Jewish Quarter). After visiting the old part of the city, the trip will continue with a visit to the small town of Figueres, the capital of Alt Empordá and birth place of Salvador Dalí who lived there until his death in 1989. Lunch will be served at the picturesque hotel Duran before visiting the well known Dalí Museum. Return to Barcelona will be around 19:00.
26‐29 July, Barcelona, Spain 22
Activity: Barcelona Modernism tour Date: Tuesday, July 28th Time: The meeting place for the tour is either at “Hotel Serhs Campus” at
9:00 or at Pl. Catalunya (outside “Hard Rock Café”) at 9:45 Price: €79 per person Duration: 5 hours Description: We will visit the Eixample district of Barcelona, an extension of the city planned by the engineer Idelfons Cerdà which hosts a great collection of the Art Nouveau buildings, a style known in Catalonia as Modernisme. The visit will start around the Paseo de Gracia at the so called Quadrat d’Or (Golden Square) where we will marvel at the architecture of buldings such the Casa Battló, Casa Lléo Morera and Casa Milá. Following this we will see the exterior of the Sagrada Familia, and then we will spend a part of the morning at the Park Güell, where the Gaudi’s Museum is located. On the way we will stop twice to have some “tapas” in the traditional Spanish way. The visit will finish after lunch and return to the “Hotel Serhs Campus” will be around 16:00. Activity: Day‐trip to Sitges Date: Wednesday, July 29th Time: Buses will pick up participants from “Hotel Serhs Campus” at 9:00 Price: €105.52 per person Duration: 8 hours Description: We will visit the seaside village of Sitges, located about 35km southwest of Barcelona. Sitges is famous for its palaces and residential houses, built by the “indians” (catalan people who emigrated to Cuba in the 18th century) after returning with their fortunes from Cube. With its parish church dominating the view and the sea and beach at is feet Sitges is a place worth visiting. The Promenade joins the old part of the town to the residential areas. We will visit the Cau Ferrat, a museum with art collections very well known around the world. Return to Barcelona will be around 17:30.
23 ICDAR 2009
Workshops
Eighth IAPR International Workshop on Graphics Recognition (GREC 2009)
Dates: July 22‐23, 2009 Location: City University of La Rochelle, France Organisers: Jean‐Marc Ogier (Université de la Rochelle, France) Liu Wenyin (City University of Hong Kong, China) Josep Lladós (Univ. Autònoma de Barcelona, Spain) The Eighth International Workshop on Graphics Recognition (GREC2009), organized by IAPR TC‐10 (Technical Committee on Graphics Recognition), will be held at the City University of La Rochelle, France on July 22‐23, 2009, just before the 10th International Conference on Document Analysis and Recognition (ICDAR), Barcelona, Spain. The GREC workshops provide an excellent opportunity for researchers and practitioners at all levels of experience to meet colleagues and to share new ideas and knowledge about graphics recognition methods. Graphics recognition is a subfield of document image analysis that deals with graphical entities in engineering drawings, maps, architectural plans, musical scores, mathematical notation, tables, diagrams, etc.
26‐29 July, Barcelona, Spain 24
Third Workshop on Analytics for Noisy Unstructured Text Data (AND 2009)
Dates: July 23‐24, 2009 Location: Convention Centre Hotel Serhs Campus, Barcelona Organisers: Daniel Lopresti (Lehigh University, USA) Shourya Roy (Xerox India Innovation Hub, India) Klaus U. Schulz (University of Munich, Germany) L. Venkata Subramaniam (IBM Research, India) AND 2009 is a workshop devoted to issues arising from the need to contend with noisy inputs, the impact noise can have on downstream applications, and the demands it places on document analysis. The Third Workshop on Analytics for Noisy Unstructured Text Data will build on two previous successful AND workshops held in 2007 (in conjunction with the 20th Joint Conference on Artificial Intelligence [IJCAI]) and in 2008 (in conjunction with the 31st Annual International ACM SIGIR Conference).
International Workshop on Multilingual OCR (MOCR)
Dates: July 25, 2009 Location: Convention Centre Hotel Serhs Campus, Barcelona Organisers: Venu Govindaraju (University at Buffalo, USA) Prem Natarajan (BBN Technologies, USA) The objective of the MOCR workshop will be to explore methodologies for multilingual document analysis systems with particular focus on OCR. The scope of Multilingual OCR is defined to include systems that are capable of reading more than one language in the same document, as well as one‐language‐per‐document systems that can be easily retargeted to new languages. The workshop will provide a forum for technical discussions on three important themes: progress in the last decade, hard open research problems, and proven methods.
25 ICDAR 2009
Third International Workshop on Camera‐Based Document Analysis and Recognition (CBDAR 2009)
Dates: July 25, 2009 Location: Convention Centre Hotel Serhs Campus, Barcelona Organisers: Thomas Breuel (Tech. Univ. of Kaiserslautern / DFKI, Germany) Seiichi Uchida (Kyushu University, Japan) Pervasive use of camera phones and hand‐held digital still and video cameras have let us discover that image‐based recording of information by just pressing a button is really convenient. In addition to imaging faces and scenes, people have started capturing documents to preserve contents. Cameras, which are now functioning as personal copiers, will soon produce a huge number of imaged documents that are beyond manual handling. Although traditional techniques developed in the field of document analysis and recognition provide us with a good starting point, they cannot be directly used on camera captured images. This leads us to a new sub‐field of research. CBDAR is the international workshop with a special focus on camera captured documents. Presentation of up‐to‐date issues and techniques as well as discussions on future directions will boost research in this relatively new area. Participants will share experiences and problems in the area. In the past, the First CBDAR (2005) and the Second CBDAR (2007) were held at Seoul, Korea and Curitiba, Brazil, respectively, as a satellite conference of ICDAR.
26‐29 July, Barcelona, Spain 26
Tutorials Four tutorials will take place on Sunday July 26th (the day before the main conference starts). Registration is available through the conference Web site.
Interactive Multimodal Transcription of Handwritten Text Images
Date: July 26, 2009 Time: 09:00‐13:30h Room: Lluís Vives I Presenters: Enrique Vidal (Universidad Politécnica de Valencia, Spain) Alejandro Tosselli (Universidad Politécnica de Valencia, Spain) Description: In this course we look at MM‐CATTI (Multimodal Computer Assisted Transcription of Text Images) from a general paradigm of Human‐Interaction in Pattern Recognition and examine the important challenges and interesting research opportunities entailed the resulting framework. In particular we show how to take direct advantage of the feedback information provided by the user in each interaction step to improve raw recognition performance. We also argue that human interaction naturally entails multimodal processing and show how this fact can lead to improve overall system behaviour and usability. Biographical Notes Enrique Vidal received the Licenciado degree in Physics in 1978 and the Doctor en Ciencias Físicas degree (Ph.D. in Physics) in 1985, both from the Universitat de València. From 1978 to 1986 he was with this University serving in computer system programming and teaching positions. In the same period he coordinated a research group in the fields of Pattern Recognition and Automatic Speech Recognition. In 1986 he joined the Departamento de Sistemas Informáticos y Computación of the Universidad Politécnica de Valencia (UPV), where he is until now serving as a full professor of the Facultad de Informática. In 1995 he joined the Instituto Tecnológico de Informática, where he has been coordinating several projects on Pattern Recognition and Machine Translation. He is co‐leader of the Pattern Recognition and Human Language Technology group of the UPV.
27 ICDAR 2009
His current fields of interest include Statistical Pattern Recognition, Multimodal Interaction and applications to Speech, Language and Image processing. In these fields, he has published more than two hundred papers in relevant journals, conference proceedings and books. Dr. Vidal is a member of the Spanish Society for Pattern Recognition and Image Analysis (AERFAI) and the International Association for Pattern Recognition (IAPR).
Alejandro H. Toselli received the M.S. degree in electrical engineering from Universidad Nacional de Tucumán (Argentina) in 1997 and the Ph.D. degree in Computer Science from Universidad Politécnica de Valencia (Spain) in 2004. His current research interest lies in the subject of Computer Assisted and Multimodal Interaction in Pattern Recognition Systems: Handwritten Text Recognition/Transcription Applications. Dr. Alejandro is a member of the Spanish Society for Pattern Recognition and Image Analysis (AERFAI) and the International Association for Pattern Recognition (IAPR).
26‐29 July, Barcelona, Spain 28
Forensic Document Examiners Approach To Handwriting Comparisons / Identification
Date: July 26, 2009 Time: 09:00‐13:30h Room: Lluís Vives II Presenters: Samiah Ibrahim (Canada Border Services Agency) Elisa van den Heuvel (Netherlands Forensic Institute) Description: Forensic document examination is a diverse field that includes the analysis and comparison of information that appears in many forms on documents, but we will limit the tutorial to the subject of the determination of authorship. This half‐day tutorial will cover the historical and current approach taken by forensic document examiners in handwriting and signature examinations. Topics for the tutorial include: history of the discipline; class versus individual characteristics; variation; statistical approaches; genuineness versus spuriousness; opinions and conclusions. Biographical Notes Samiah Ibrahim is presently a forensic scientist with the Forensic Document Section of the Canada Border Services Agency. In this function Samiah is responsible for conducting forensic analysis of questioned document cases involving multiple facets of examination including, but not limited to: handwriting, signatures, typewriters, impact & non‐impact printing devices, photocopiers, decipherment of latent impressions, detection & decipherment of obliterations, commercial & security printing processes, wet & dry cachets, and examination of official documents (i.e. passports, birth certificates, driver’s licenses).
Samiah earned a B.Sc. in Biology (1989) and a B.A. in Political Science (1987), both from Carleton University in Ottawa. From here Samiah joined the Canadian Security Intelligence Service where she received her forensic document examination training. Samiah joined the Canada Border Services Agency in 2004 having worked for several Canadian federal government departments in the interim. Samiah co‐presented this tutorial incorporating forensics with document analysis and recognition at ICDAR 2007. She has presented various research papers at conferences and considers spectral differences in ink and biometrics as topics of interest. She is an active member of the American Society of Forensic Document Examiners and is the Program Chair for the 2010 Annual General Meeting in Victoria, Canada.
29 ICDAR 2009
Elisa van den Heuvel started in 2005 as scientific forensic handwriting expert in training at Netherlands Forensic Institute. Her scientific background lies primarily in human motor control with special emphasis on handwriting/signature movement execution. In chronology, she received her M.Sc. from Radboud University of Nijmegen in 1996, and her Ph.D. at Vrije Universiteit Amsterdam (VUA) in 2000. During her PhD research Elisa also worked at Motor Control Lab, Arizona State University, Tempe, USA as a visiting research scholar. In 2000, she started postdoctoral work at Biomechanics at VUA where she studied preclinical symptoms of Parkinson’s disease. Since 1997, Elisa has published several scientific journal articles and peer‐reviewed conference articles. She co‐presented a Tutorial at ICDAR in 2007 on Computational Forensics, and is involved in the organization of the ICDAR 2009 Signature Verification Competition for on‐ and offline skilled forgeries (SigComp09).
26‐29 July, Barcelona, Spain 30
Digital Libraries and Historical Document Processing
Date: July 26, 2009 Time: 14:30‐18:50h Room: Lluís Vives I Presenters: Apostolos Antonacopoulos (University of Salford, UK) Simone Marinai (Università di Firenze, Italy) Description: The tutorial will cover the background issues, challenges and opportunities in the analysis of historical documents and their applications in the Digital Library world. The tutorial is divided in four parts. The first part proposes a survey of the aims of Digital Libraries and their
technical evolution over the years. Potential applications of Document Image Analysis techniques in the field of DLs are pointed out and discussed with the audience. The use of open source software for building simple digital library infrastructures are analyzed as well. The second part starts with an examination of the different motivation and
other institutional factors that influence technical decisions. The types of documents typically encountered are discussed next with the challenges and possibilities they offer for digitization and full‐text conversion. Focusing on the needs of major libraries, the remainder of this part presents in detail the different stages in full‐text conversion. In each of the stages (scanning, image enhancement, segmentation, OCR and post‐processing) the challenges and possibilities for improvement are examined. The third part deals with recent advances in Document Image Retrieval (DIR)
and potential applications of these techniques in the field of DL. Two main paradigms will be described: retrieval by layout similarity and text‐based retrieval. These techniques will be explained also through the demonstration of a DIR system specifically developed for the use on DL‐related documents. The fourth part of the tutorial comprises a more technical description of the
state‐of‐the‐art in the analysis of historical documents. Major past and current initiatives will be mentioned and individual methods will be described for each stage in the processing, analysis and recognition of historical documents. Finally, as an essential aspect in measuring and making progress, ways of performance evaluation of historical document analysis methods will be presented.
31 ICDAR 2009
Apostolos Antonacopoulos is currently a Senior Lecturer in Pattern Recognition and heads the Pattern Recognition and Image Analysis (PRImA) research group at the University of Salford, UK. He received his PhD from the University of Manchester Institute of Science and Technology (UMIST), UK in 1995. For his early research in Document Image Analysis he was presented with the Best Student Paper Award at the International Association for Pattern Recognition (IAPR) workshop on Document Analysis Systems in 1994 (DAS'94). In 2005, he received the IAPR/ICDAR Young Investigator Award for "outstanding service to the ICDAR community and his innovative research in historical document processing applications."
Dr Antonacopoulos is a member of the Editorial Boards of the International Journal on Document Analysis and Recognition (IJDAR) and of the Electronic Letters on Computer Vision and Image Analysis (ELCVIA) journal, Chair of the IAPR Conferences and Meetings Committee, Vice‐Chair of the IAPR Technical Committee on Reading Systems (TC11), past Chair of the IAPR Education Committee, Advisory Board member of ICDAR, Program Co‐Chair or ICDAR2009, Chair (Publications) of ICDAR2003, Chair (Tutorials and Demos) ICFHR2008, Co‐Chair of WDA2001 and WDA2003, and a Program Committee member of most current and recent editions of conferences in his field of research: ICPR, ICDAR, DAS, ACM DocEng, SPIE DRR, ACM SAC etc. He is a member of the IET (MIET), the IEEE and the IEEE Computer Society, the ACM and the British Machine Vision Association. In 2007 he co‐edited a special issue on the Analysis of Historical Documents in the International Journal of Document Analysis and Recognition. He currently (2008‐2011) plays a leading role in the largest to‐date EU‐funded project in Digital Libraries and Cultural Heritage: IMPACT (Improving Access to Text) carrying out research in full‐text conversion of historical documents in the leading libraries of Europe.
Simone Marinai is currently an Assistant Professor at the University of Firenze, Italy. He received his PhD from the University of Firenze, Italy in 1996. Dr Marinai is a member of the Editorial Boards of the International Journal on Document Analysis and Recognition (IJDAR) and of the Electronic Letters on Computer Vision and Image Analysis (ELCVIA) journal; Past chair of the IAPR Technical Committee on Neural Networks and Computational Intelligence (TC3); Steering Committee member of DAS and DIAL workshops; Publicity Co‐Chair or ICDAR‐2009; Co‐chair of DAS 2004, ANNPR 2003, ANNPR 2006, ANNPR 2008, NNLDAR 2005, DAUDD 1999; Program Committee member of most current and recent editions of conferences in various research fields: ICPR, ICDAR, DAS, DEXA, among the others. He is co‐editor of the book "Machine Learning in Document Analysis and Recognition" published by Springer Verlag in 2008.
26‐29 July, Barcelona, Spain 32
Pattern Recognition Systems – Conception, Evaluation and Improvement
Date: July 26, 2009 Time: 14:30‐18:50h Room: Lluís Vives II Presenters: Volker Märgner (Technische Universitaet Braunschweig, Germany) Haikal El Abed (Technische Universitaet Braunschweig, Germany) Description: The aim of the tutorial “Pattern Recognition Systems – Conception, Evaluation and Improvement” is to lay the foundations and to encourage further discussions on the development of pattern recognition systems, especially for the recognition of printed or handwritten text. Researchers and practitioners working in the field of pattern recognition will be introduced to handwritten text recognition systems in general, steps of a system evaluation process and techniques to improve recognition quality. The objective of this tutorial is to provide a basis for researchers to improve the quality and performance of a recognition system. The presented methods include detailed analysis of a recognition system, relation between structured data and performance of systems, reject / combination strategies, and post‐processing approaches. After this tutorial participants should be able to design their own recognition system or improve an existing one. Biographical Notes Volker Märgner: received his Diploma (Dipl.‐Ing.) and Doctorate (Dr.‐Ing.) degrees in electrical engineering from the Technical Univ. Braunschweig (Germany) in 1974 and 1983, respectively. Since 1983, he has been working at Technical Univ. Braunschweig. His main focus of research is in image processing and pattern recognition. Currently, he is working on image pre‐processing and pattern recognition methods and their application to industrial quality control as well as to the recognition of cursive handwriting on paper documents. He is a member of VDE/VDI, DAGM, IAPR, and IEEE.
Haikal El Abed: is a researcher at the Braunschweig Technical University, Germany. Since 2001, he has been working at the Institute for Communications Technology (IfN), Department of Signal Processing for Mobile Information Systems. He has specialized in image and signal processing document analysis systems design and configuration, and Arabic manuscripts recognition. He is a member of IEEE, DAGM, IAPR, VDE/VDI.
33 ICDAR 2009
Awards The IAPR Technical Committees on Graphics Recognition (TC10) and Reading Systems (TC11) are pleased to announce the recipients of the IAPR/ICDAR 2009 Awards. The IAPR/ICDAR Outstanding Achievements Award is presented to Prof. Horst Bunke for his outstanding and continued contributions to research and education in handwriting recognition and document analysis, and services to the community. Prof. Bunke will deliver the Opening Keynote Speech at ICDAR2009 in Barcelona on July 27, 2009.
The IAPR/ICDAR Young Investigator Award is presented to Prof. Katrin Franke for her outstanding contributions to handwriting analysis and computational forensics. Congratulations to the awardees!
ICDAR 2009 Awards Committee David Doermann (IJDAR EIC) Hiromichi Fujisawa (Previous winner of Outstanding
Achievements Award) Jianying Hu (TC11 representative / previous TC11 Chair) Josep Lladós (Current ICDAR chair /
Previous winner of Young Investigator Award) Dan Lopresti (TC11 Chair) Karl Tombre (TC10 representative) Liu Wenyin (TC10 Chair)
26‐29 July, Barcelona, Spain 34
Biographical Notes Prof Horst Bunke received his M.S. and Ph.D. degrees in Computer Science from the University of Erlangen, Germany. In 1984, he joined the University of Bern, Switzerland, where he is a professor in the Computer Science Department. He was Department Chairman from 1992 ‐ 1996, Dean of the Faculty of Science from 1997 to 1998, and a member of the Executive Committee of the Faculty of Science from 2001 to 2003.
From 1998 to 2000 Horst Bunke served as 1st Vice‐President of the International Association for Pattern Recognition (IAPR). In 2000 he also was Acting President of this organization. Horst Bunke is a Fellow of the IAPR, former Editor‐in‐Charge of the International Journal of Pattern Recognition and Artificial Intelligence, Editor‐in‐Chief of the journal Electronic Letters of Computer Vision and Image Analysis, Editor‐in‐Chief of the book series on Machine Perception and Artificial Intelligence by World Scientific Publ. Co., Advisory Editor of Pattern Recognition, Associate Editor of Acta Cybernetica and Frontiers of Computer Science in China, and former Associate Editor of the International Journal of Document Analysis and Recognition, and Pattern Analysis and Applications.
Horst Bunke received an honorary doctor degree from the University of Szeged, Hungary, and held visiting positions at the IBM Los Angeles Scientific Center (1989), the University of Szeged, Hungary (1991), the University of South Florida at Tampa (1991, 1996, 1998‐2007), the University of Nevada at Las Vegas (1994), Kagawa University, Takamatsu, Japan (1995), Curtin University, Perth, Australia (1999), and Australian National University, Canberra (2005).
He served as a co‐chair of the 4th Int. Conference on Document Analysis and Recognition held in Ulm, Germany, 1997 and as a Track Co‐Chair of the 16th and 17th Int. Conference on Pattern Recognition held in Quebec City, Canada and Cambridge, UK in 2002 and 2004, respectively. Also he was chairman of the IAPR TC2 Workshop on Syntactic and Structural Pattern Recognition held in Bern 1992, a co‐chair of the 7th IAPR Workshop on Document Analysis Systems held in Nelson, NZ, 2006, a co‐chair of the 10th Int. Workshop on Frontiers in Handwriting Recognition, held in La Baule, France, 2006, and a program co‐chair of the 11th Int. Conference on Frontiers in Handwriting Recognition held in Montreal, Canada, 2008. Horst Bunke was on the program and organization committee of many other conferences and served as a referee for numerous journals and scientific organizations. He is on the Scientific Advisory Board of the German Research Center for Artificial Intelligence (DFKI). Horst Bunke has more than 600 publications, including 40 authored, co‐authored, edited or co‐edited books and special editions of journals.
35 ICDAR 2009
Katrin Franke is presently associate professor at the Norwegian Information Security laboratory in Gjøvik, Norway. In 2005 she obtained her Ph.D. degree at the Artificial Intelligence Institute, University of Groningen, The Netherlands. She is an alumni of the Technical University of Dresden in Germany.
After graduating in 1994, Mrs. Franke began to conduct research at the Fraunhofer IPK in Berlin, Germany. The institute belongs to the Fraunhofer Society, a non‐profit organization, conducting applied research on behalf of industrial and governmental entities. Mrs. Franke carried out extensive research on digital image processing and pattern recognition at Fraunhofer IPK. Until December 2006, she has worked as a scientific project manager; leading research teams as well as internationally distributed project consortia. Katrin Franke was in charge of founded research and industrial projects on document processing, signature and custom stamp analysis, applied in banking and in forensics. These projects have brought forth software modules and software systems, now operating in banks in Germany, the United Kingdom, South Africa and Jamaica as well as in forensic laboratories in Germany.
In 2007 Katrin Franke joined the Norwegian Information Security laboratory at Gjøvik University College in Norway. She conducts research in Computational Forensics, supervises Ph.D. projects and teaches courses in Machine Learning and Pattern Recognition at the PhD and master level. Currently, she is appointed in the Research and Advisory board at Gjøvik University College.
Mrs. Franke has published more that 70 scientific papers including one patent. She regularly reviews technical papers for research organizations, international conferences, and some leading scientific journals, like IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), International Journal on Document Analysis and Recognition (IJDAR) where she also serves as an associate editor.
She is a member of the World Federation on Soft Computing (WFSC) and the World‐Wide‐Web Consortium (W3C) where she contributes to the international standardization of InkML, an Xml‐application for handwriting data. She is a member of several international program committees. She is involved in the organization of international conferences; the most prominent among them is the International Workshop on Computational Forensics (IWCF). Mrs. Franke is a founding member of the IAPR‐TC6 on Computational Forensics founded in 2008 and serves currently as its chair.
26‐29 July, Barcelona, Spain 36
Invited Talks
IAPR/ICDAR Award Lecture: Graph‐based Representations in Document Analysis
Horst Bunke Institute of Computer Science and Applied Mathematics University of Bern, Switzerland Abstract. Graph representation is a powerful formalism that has found widespread applications in science and engineering. Particularly in the field of document analysis, graphs have been used very successfully. Examples include layout analysis, graphics recognition, machine printed character recognition, and handwriting recognition. In this talk we first review some of these applications. Then we report novel approaches to classification, clustering, and related tasks based on graph representations. We will discuss in particular graph kernels and graph embedding in vector spaces and show how they can be used in document analysis. Biography. Horst Bunke is a professor of Computer Science at the University of Bern, Switzerland. He served as the 1st Vice‐ and the Acting President of the International Association for Pattern Recognition (IAPR) in 1998 – 2000. He is a Fellow of the IAPR, former Editor‐in‐Charge of the International Journal of Pattern Recognition and Artificial Intelligence, Editor‐in‐Chief of the journal Electronic Letters of Computer Vision and Image Analysis, Editor‐in‐Chief of the book series on Machine Perception and Artificial Intelligence by World Scientific Publ. Co., Advisory Editor of Pattern Recognition, and an Associate Editor of several other journals. He received an honorary doctor degree from the University of Szeged, Hungary, and held visiting positions at many institutions world wide. Horst Bunke has been working in the fields of Computational Intelligence, Pattern Recognition and Machine Learning for more than thirty years. He has more than 600 publications, including 40 authored, co‐authored, edited or co‐edited books and special editions of journals.
37 ICDAR 2009
Keynote 1: Mass Digitisation in Digital Libraries: The Experience of the British Library
Aly Conteh Head of Digitisation, British Library London, UK Abstract. The British Library is one of the great research libraries of the world, holding over 150 million items in all known languages and formats. The advent of the Internet and the ability to digitise large quantities of text and images and make them available over the Web has transformed ways of working. For the past two decades, the British Library has undertaken a number of focused digitisation initiatives. More recently, we have entered the world of mass digitisation of newspapers and books. Using the experience gained from digitising 25 million pages of books and 4 million pages of newspapers dating from the early 17th century, the approach, challenges and lessons learnt will be presented. For institutions such as the British Library partnering with the document analysis and recognition community is a key part of creating valuable and enduring resources for scholars and the public alike. The partnerships that the Library is currently involved in, which seek to advance the state of the art in mass digitisation of historic text, will be presented. Biography. Aly Conteh is the Digitisation Programme Manager at the British Library, a post he took up in April 2003. He is responsible for the development and implementation of the policies, workflows and standards which govern digitisation of items from the Library's vast collections. He has been involved in many digitisation projects at the British Library including projects to digitise 25 million pages of 19th Century books, 4 million pages of pre‐1900 newspapers and hundreds of manuscript volumes. His background is in IT and prior to joining the British Library he implemented a large scale digitisation workflow at a commercial publisher. He serves on the Executive Board for the IMPACT project a large‐scale integrating project funded by the European Commission as part of the Seventh Framework Programme (FP7). He is as a member of the European Commission’s Member States’ Expert Group on Digitisation and Digital Preservation and has advised UK government departments on digitisation matters.
26‐29 July, Barcelona, Spain 38
Keynote 2: Ontology‐Based Document Understanding on the Semantic Desktop
Andreas Dengel German Research Centre for Artificial Intelligence (DFKI) Kaiserslautern, Germany Abstract. A document is the principal mode of preserving and transporting knowledge through time and space. Documents are both sources of information as well as a means for communication. The information they contain can be for example the basis for satisfying potential customers, for defining a common understanding, for assessing facts and interrelationships, for establishing valuable contacts, for planning new products or education in an as yet unknown area. The decreasing half‐life‐period of knowledge along with the constant growth of highly diverse and specialized information in almost any field ask for intelligent individualized human centered technologies assisting the “knowledge worker” in order to keep track of and cope with documents and information, and to efficiently manage vital business processes. As one promising approach, I like to present the paradigm of the Semantic Desktop as a means for document understanding and for managing all personal information across application borders using Semantic Web standards. A Semantic Desktop acts as an extended personal memory assisting users to file, relate, share, and access all digital information like documents, multimedia, and messages through a Personal Information Model (PIMO). This PIMO is build on ontological knowledge generated through user observations and interactions with documents and may be seen as a formal and semi‐formal complement of the user's mental models. In this talk I will motivate the need for such tools, describe the basic idea and mechanisms for a socio‐technical document analysis, and show how a semantic Desktop may act as a personal information butler in order to provide proactive and adaptive information support. Biography. Andreas Dengel is a member of the Management Board as well as Scientific Director at the German Research Center for Artificial Intelligence (DFKI) in Kaiserslautern where he is leading the Knowledge Management research department.
39 ICDAR 2009
In 1993 he was appointed Professor at the Computer Science Department of the University of Kaiserslautern where he holds the chair “Knowledge‐Based Systems”.
From 1980 to 1986 Andreas studied Computer Science and Economics at the University of Kaiserslautern. He subsequently worked at the Siemens research lab in Munich and at the University of Stuttgart where he completed his doctoral thesis in 1989. In 1991 he worked as a guest researcher at Xerox Parc in Palo Alto. Andreas is a member of the IT‐Summit Working Group on “service and consumer‐oriented information technology” of the German government and acts as an expert for the German Council of Science and Humanities.
In 2008 he co‐founded the Institute on Document Analysis and Knowledge Science (IDAKS) at the Osaka Prefecture University in Japan. Andreas is a advisory board member of ICDAR, of the Center of Excellence on Semantic Technologies at MIMOS in Kuala Lumpur, Malaysia, of the NEC Computers and Communication Innovation Research Labs (CCIL), and others. Formerly, he was the German representative in the IST Prize Executive Jury of the European Council of Applied Science (Euro‐CASE) a lecturer of the Joint Executive MBA course at the Johannes Gutenberg University at Mainz, the University of Texas at Austin, and the Dongbei University of Finance and Economics at Dalian, China. From 1997 to 2001 Andreas was a member of the METTREC Planning Committee ((Metadata/Text Retrieval Conference Committee) of the National Institutitute for Standards and Technology (NIST) in the United States.
Andreas was program/technical chair of ICPR, ICDAR, DAS, and conferences in other AII areas. Moreover, he is founder or initiator of several successful start‐up companies. In 2005 he received a “Pioneer Spirit Award” for one of his start‐up concepts. He is co‐editor of various international computer science journals, has written or edited 8 books, and is author of more than 150 peer‐reviewed scientific publications. He supervised more than 120 PhD and master theses.
In 2004, Andreas has been elected a Fellow of the International Association for Pattern Recognition (IAPR) and has been honored for his work several times. Most prominent prizes are the ICDAR “Young Investigator Award”, the Nakano Award, the Technical Communication Award of the Alcatel SEL Foundation, the Multi‐Media Award of the State Rheinland‐Pfalz as well as a Document Analysis Systems Achievement Award. His main scientific emphasis is in the areas of Document Understanding, Knowledge Management, and Artificial Intelligence.
26‐29 July, Barcelona, Spain 40
Keynote 3: Enterprise Approach to OCR Technology Development
Andrey Isaev Director of Technology Products Department, ABBYY Moscow, Russia Abstract. The talk presents an overview of the approaches necessary to build the best commercial OCR technology. Commercial OCR technology vendors face significant challenges that academy researchers don't have to take care of. The more popular a technology is, the more important it is to keep recognition results consistent among different versions of the technology SDK in all usage scenarios it is being employed, regardless of any improvements in architecture and algorithms. OCR technology has much more quality parameters than just recognition accuracy, and in different usage scenarios different parameters are important. Thus the best technology has to be best in all aspects. Moreover, during past decades industry has redefined the term OCR which now means much more that just character recognition. This talk attempts to discuss these challenges and their influence on the research and development process. Biography. Andrey Isaev has more than 10 years of experience in the software industry. He joined ABBYY in 2007 to lead its OCR SDK division. His responsibilities cover the full cycle from scientific research goal setting and the management of a team of engineers to market analysis and development. Before joining ABBYY, Andrey was leading R&D in the mobile software and handwriting recognition division at Paragon Software. Andrey earned a Master of Science degree in Management and Applied Mathematics from Moscow Institute of Physics and Technology.
41 ICDAR 2009
Keynote 4: Ten editions of ICDAR: Overview and Outlook
Guy Lorette MR IRISA, Université de Rennes 1 Université Européenne de Bretagne, France Abstract. After ten editions of ICDAR, it seems to be now time and necessary to do a backtracking for making an overview and a retrospective of what happened during this period of time in our research domain. At first, in this talk the general scientific environment and the evolution of ICDAR features over time will be presented. Then, after a brief historical view and a summary of the main topics of each of the ten ICDAR, the major facts, milestones and results will be put into perspective. Past evolutions, recent achievements and future trends will be analyzed in order to extract some useful know‐how and skills. This talk will point out the major advances accomplished in the domain of digital document processing, analysis, recognition and understanding, over a period of almost two decades (1991‐2009). These advances will be analyzed in terms of: research avenues, models, methods, standards, languages, systems, hardware, software, experimentations, application domains, industrial products, success and failures, etc. Future prospects, trends and challenges will be highlighted. Finally, some guidelines will also be suggested. Biography. Guy Lorette is currently a professor in computer science and image processing at the Rennes 1 University. He received his engineer diploma (in 1967) and his engineer‐doctor degree (in 1970) from the INSA, Lyon, and his “doctorat ès sciences physiques” (in 1983) from the Paris 12 Val de Marne University.
From1967 until 1972, he was an Assistant Prof. in electrical engineering at the INSA, Lyon. From 1972 until 1987 he was an Associate Prof. in Electronic and Image processing at the Paris 12 Val de Marne University. In 1987, as Prof., he joined the Rennes 1 University and the IRISA laboratory, a joint research laboratory from INRIA, CNRS, Rennes 1 University, INSA and the ENS Cachan. His current research activities, within the Imadoc research team, are in the field of cursive handwriting recognition, image processing and man‐document interaction.
Professor Lorette was general co‐chair of several international conferences. i.e. ICDAR’91, the first International Conference on Document Analysis and Recognition held in Saint‐Malo (France) in 1991, ICPR held in Hong‐Kong in 2006 and two Korean‐
26‐29 July, Barcelona, Spain 42
French workshops. He was also general co‐chair of IWFHR 9 and of IWFHR10, the International Workshop on Frontiers in Handwriting Recognition. He was program co‐chair of ICDAR 1995 and member of 38 other program committees. He is also one of the founder members of EVODIA, a French firm in the domain of document image processing.
He was an active member of several professional societies, namely the IAPR, IEEE, IGS, GRCE, AFRIF and an Associate Editor of the International Journals: “Pattern Recognition”, “International Journal on Pattern Recognition and Artificial Intelligence”, “International Journal on Document Analysis and Recognition”. He is also a member of the advisory board of Unipen.
43 ICDAR 2009
Technical Programme
Information for Session Chairs The chair of each session is expected to arrive at the session room at least 10 minutes before the session begins, and to check the attendance of speakers in the session according to the schedule. Each speaker has 20 minutes for both presentation and discussion. In case of no‐shows, please refrain from rescheduling the remaining oral presentations in order to facilitate participants to attend to the presentations they plan to.
Information for Oral Sessions Presenters at all sessions are required to show up at the session 10 minutes in advance of the first paper. All presenters are limited to 20 minutes presentation and discussion. The session chair will notify you once 15 minutes have elapsed, at which time you should aim to sum up and close your presentation. It is necessary to start on schedule so people moving between sessions can attend to the presentations they plan to. All session rooms are equipped with a computer and a projector. Presenters can make use of the conference computer or connect their own laptop. You should aim to copy your presentations over, or connect your laptops before the session begins to avoid any delays.
Information for Poster Sessions All poster sessions will take place in a part of the “Arnau de Vilanova” hall. Boards sized 95cm (width) by 140cm (height) will be provided for each paper. Each paper’s code will be shown on the board, as well as on the list of posters for the day. Please mount your poster early in the morning before the first coffee break and remove it after the poster session. We encourage presenters to stay close to their posters during the coffee breaks. All presenters are required to be by their posters during the poster session for anticipated discussion with the participants.
26‐29 July, Barcelona, Spain 44
Sunday, July 26th
0800 – 0900 Registration
0900 – 1100 Tutorial 1: Interactive Multimodal Transcription of Handwritten Text Images (Part I)
Location: Lluís Vives I Organisers: E. Vidal (Universidad Politécnica de Valencia, Spain) A. Tosselli (Universidad Politécnica de Valencia, Spain)
0900 – 1100 Tutorial 2: Forensic Document Examiners Approach to handwriting Comparisons / Identification (Part I)
Location: Lluís Vives II Organisers: S. Ibrahim (Canada Border Services Agency) E. van den Heuvel (Netherlands Forensic Institute)
1100 – 1130 Coffee Break Location: Patio
1130 – 1330 Tutorial 1: Interactive Multimodal Transcription of Handwritten Text Images (Part II)
Location: Lluís Vives I Organisers: E. Vidal (Universidad Politécnica de Valencia, Spain) A. Tosselli (Universidad Politécnica de Valencia, Spain)
0900 – 1100 Tutorial 2: Forensic Document Examiners Approach to handwriting Comparisons / Identification (Part II)
Location: Lluís Vives II Organisers: S. Ibrahim (Canada Border Services Agency) E. van den Heuvel (Netherlands Forensic Institute)
1330 – 1430 Lunch Location: Sirius Restaurant
45 ICDAR 2009
1430 – 1630 Tutorial 3: Digital Libraries and Historical Document Processing (Part I)
Location: Lluís Vives I Organisers: A. Antonacopoulos (University of Salford, UK) S. Marinai (Universit`a di Firenze, Italy)
1430 – 1630 Tutorial 4: Patter Recognition Systems: Conception, Evaluation and Improvement (Part I)
Location: Lluís Vives II Organisers: V. Märgner (Technische Universitaet Braunschweig, Germany) H. El Abed (Technische Universitaet Braunschweig, Germany)
1630 – 1650 Coffee Break Location: Patio
1650 – 1850 Tutorial 3: Digital Libraries and Historical Document Processing (Part II)
Location: Lluís Vives I Organisers: A. Antonacopoulos (University of Salford, UK) S. Marinai (Universit`a di Firenze, Italy)
1650 – 1850 Tutorial 4: Recognition Systems: Conception, Evaluation and Improvement (Part II)
Location: Lluís Vives II Organisers: V. Märgner (Technische Universitaet Braunschweig, Germany) H. El Abed (Technische Universitaet Braunschweig, Germany)
1900 – 2100 Welcome Reception Location: Entrance Square, Hotel Serhs Campus
26‐29 July, Barcelona, Spain 46
Monday, July 27th
0800 – 0900 Registration
0900 – 0920 Opening Ceremony Location: Arnau de Vilanova
0920 – 1020 IAPR / ICDAR Award Lecture Location: Arnau de Vilanova Chair: Hiromichi Fujisawa (Hitachi R&D, Japan)
0920 Graph‐based Representations in Document Analysis Horst Bunke
1020 – 1040 Coffee Break Location: Patio
1040 – 1200 Session 1.1: Character and Text Segmentation and Extraction
Location: Arnau de Vilanova Chair: Ching Suen (Concordia University, Canada)
1040 Text Detection and Localization in Complex Scene Images using Constrained AdaBoost Algorithm Shehzad Muhammad Hanif, Lionel Prevost
1100 Text Localization in Natural Scene Images Based on Conditional Random Field Yi‐Feng Pan, Xinwen Hou, Cheng‐Lin Liu
1120 Multi‐Oriented and Multi‐Sized Touching Character Segmentation Using Dynamic Programming Partha Pratim Roy, Umapada Pal, Josep Lladós, Mathieu Delalandre
1140 Conspicuous Character Patterns Seiichi Uchida, Ryoji Hattori, Masakazu Iwamura, Shinichiro Omachi, Koichi Kise
47 ICDAR 2009
1040 – 1200 Session 1.2: Learning Techniques for Handwriting Recognition
Location: Lluís Vives I Chair: Jianying Hu (IBM T.J. Watson Research Center, USA)
1040 Writer Adaptive Training and Writing Variant Model Refinement for Offline Arabic Handwriting Recognition Philippe Dreuw, David Rybach, Christian Gollan, Hermann Ney
1100 Semi‐supervised Learning for Handwriting Recognition Gregory R. Ball, Sargur N. Srihari
1120 Evaluating Retraining Rules for Semi‐Supervised Learning in Neural Network Based Cursive Word Recognition Volkmar Frinken, Horst Bunke
1140 Design Compact Recognizers of Handwritten Chinese Characters Using Precision Constrained Gaussian Models, Minimum Classification Error Training and Parameter Compression Yongqiang Wang, Qiang Huo
1040 – 1200 Session 1.3: Forensic Document Analysis Location: Lluís Vives II Chair: Robert Sabourin (École de Technologie Supérieure, Canada)
1040 On‐Line Signature Verification: Directional Analysis of a Signature Using Weighted Relative Angle Partitions for Exploitation of Inter‐Feature Dependencies Muhammad Talal Ibrahim, Matthew Kyan, M. Aurangzeb Khan, Khurram Saleem Alimgeer, Ling Guan
1100 Biometric Person Authentication Method Using Camera‐Based Online Signature Acquisition Daigo Muramatsu, Kumiko Yasuda, Takashi Matsumoto
1120 Toward Resisting Forgery Attacks via Pseudo‐Signatures Jin Chen, Daniel Lopresti, Fabian Monrose
1140 Impact of Alphabet Knowledge on Online Writer Identification Guo Xian Tan, Christian Viard‐Gaudin, Alex C. Kot
26‐29 July, Barcelona, Spain 48
1210 – 1330 Session 2.1: Camera and Video Document Analysis Location: Arnau de Vilanova Chair: Koichi Kise (Osaka Prefecture University, Japan)
1210 Coupled Snakelet Model for Curled Textline Segmentation of Camera‐Captured Document Images Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel
1230 A Laplacian Method for Video Text Detection Trung Quy Phan, Palaiahnakote Shivakumara, Chew Lim Tan
1250 Using Multiple Frame Integration for the Text Recognition of Video Jian Yi, Yuxin Peng, Jianguo Xiao
1310 Real‐Time Camera‐Based Recognition of Characters and Pictograms Masakazu Iwamura, Tomohiko Tsuji, Akira Horimatsu, Koichi Kise
1210 – 1330 Session 2.2: Online Handwriting Analysis and Recognition ‐ I
Location: Lluís Vives I Chair: Lambert Schomaker (University of Groningen, The Netherlands)
1210 Fast Incremental Learning Strategy Driven by Confusion Reject for Online Handwriting Recognition Abdullah Almaksour, Eric Anquetil
1230 Learning and Adaptation for Improving Handwritten Character Recognizers Naveen Chandra Tewari, Anoop M. Namboodiri
1250 Writer Adaptive Online Handwriting Recognition Using Incremental Linear Discriminant Analysis Zhibin Huang, Kai Ding, Lianwen Jin, Xue Gao
1310 Using Mouse Feedback in Computer Assisted Transcription of Handwritten Text Images Verónica Romro, Alejandro H. Toselli, Enrique Vidal
49 ICDAR 2009
1210 – 1330 Session 2.3: Information Spotting Location: Lluís Vives II Chair: Raghavan Manmatha (University of Massachusetts, USA)
1210 Seal Detection and Recognition: An Approach for Document Indexing Partha Pratim Roy, Umapada Pal, Josep Lladós
1230 Fisher Kernels for Handwritten Word‐spotting Florent Perronnin, Jose A. Rodriguez‐Serrano
1250 Logo Spotting by a Bag‐of‐words Approach for Document Categorization Marçal Rusiñol, Josep Lladós
1310 Slit Style HOG Feature for Document Image Word Spotting Kengo Terasawa, Yuzuru Tanaka
1330 – 1430 Lunch Location: Martí Franqués
1430 – 1600 Poster Session I Location: Arnau de Vilanova
PS1‐1 Geometric Centroids and their Relative Distances for Off‐line Signature Verification H.N. Prakash, D.S. Guru
PS1‐2 Offline Signature Verification Based on Pseudo‐Cepstral Coefficients Jesus Francisco Vargas Bonilla, Miguel Angel Ferrer Ballester, Carlos Manuel Travieso Gonzalez, Jesus Bernandino Alonso Hernandez
PS1‐3 Evaluation of Brute‐force Attack to Dynamic Signature Verification Using Synthetic Samples Javier Galbally, Julian Fierrez, Marcos Martinez‐Diaz, Javier Ortega‐Garcia
PS1‐4 Multi‐Exposure Document Fusion Based on Edge‐Intensities Marco Block, Maxim Schaubert, Fabian Wiesel, Raúl Rojas
PS1‐5 Text‐Tracking Wearable Camera System for the Blind Hideaki Goto, Makoto Tanaka
PS1‐6 Real‐Time Retrieval for Images of Documents in Various Languages Using a Web Camera Tomohiro Nakai, Koichi Kise, Masakazu Iwamura
26‐29 July, Barcelona, Spain 50
PS1‐7 Camera‐Based Ballot Counter George Nagy, Bryan Clifford, Andrew Berg, Glenn Saunders, Dan Lopresti, Elisa Barney Smith
PS1‐8 A Gradient Difference Based Technique for Video Text Detection Palaiahnakote Shivakumara, Trung Quy Phan, Chew Lim Tan
PS1‐9 Lexicon‐Based Word Recognition Using Support Vector Machine and Hidden Markov Model Abdul Rahim Ahmad, Christian Viard‐Gaudin, Marzuki Khalid
PS1‐10 Scene Text Extraction Using Focus of Mobile Camera Egyul Kim, SeongHun Lee, JinHyung Kim
PS1‐11 Devanagari and Bangla Text Extraction from Natural Scene Images Ujjwal Bhattacharya, Swapan Kumar Parui, Srikanta Mondal
PS1‐12 A Steerable Directional Local Profile Technique for Extraction of Handwritten Arabic Text Lines Zhixin Shi, Srirangaraj Setlur, Venu Govindaraju
PS1‐13 Text Segmentation in Colour Posters from the Spanish Civil War Era Antonio Clavelli, Dimosthenis Karatzas
PS1‐14 Ornamental Letters Image Classification Using Local Dissimilarity Maps Jérôme Landré, Frédéric Morain‐Nicolier, Su Ruan
PS1‐15 Low‐Resolution Character Recognition by Video‐Based Super‐Resolution Ataru Ohkura, Daisuke Deguchi, Tomokazu Takahashi, Ichiro Ide, Hiroshi Murase
PS1‐16 F‐ratio Based Weighted Feature Extraction for Similar Shape Character Recognition Tetsushi Wakabayashi, Umapada Pal, Fumitaka Kimura, Yasuji Miyake
PS1‐17 Combining Multiple HMMs Using On‐line and Off‐line Features for Off‐line Arabic Handwriting Recognition Mahdi Hamdani, Haikal El Abed, Monji Kherallah, Adel M. Alimi
PS1‐18 Shape Descriptor Based Document Image Indexing and Symbol Recognition Ehtesham Hassan, Santanu Chaudhury, M. Gopal
51 ICDAR 2009
PS1‐19 Language Model Integration for the Recognition of Handwritten Medieval Documents Markus Wüthrich, Marcus Liwicki, Andreas Fischer, Emanuel Indermühle, Horst Bunke, Gabriel Viehhauser, Michael Stolz
PS1‐20 Style‐Based Ballot Mark Recognition Pingping Xiu, Daniel Lopresti, Henry Baird, George Nagy, Elisa Barney Smith
PS1‐21 Recognition of Degraded Handwritten Characters Using Local Features Markus Diem, Robert Sablatnig
PS1‐22 Locally Developable Constraint for Document Surface Reconstruction Yuanlong Shao, Xinguo Liu, Xueying Qin, Yi Xu, Hujun Bao
PS1‐23 A Distance‐Based Technique for Non‐Manhattan Layout Analysis Stefano Ferilli, Marenglen Biba, Floriana Esposito, Teresa M.A. Basile
PS1‐24 OCD: An Optimized and Canonical Document Format Jean‐Luc Bloechle, Denis Lalanne, Rolf Ingold
PS1‐25 Hybrid Page Layout Analysis via Tab‐Stop Detection Raymond W. Smith
PS1‐26 Identification of Very Similar Filled‐in Forms with a Reject Option Joaquim Arlandis, Juan‐Carlos Perez‐Cortes, Emilio Ungria
PS1‐27 Metadata Extraction from PDF Papers for Digital Library Ingest Simone Marinai
PS1‐28 Form Field Frame Boundary Removal for Form Processing System in Gurmukhi Script Dharam Veer Sharma, Gurpreet Singh Lehal
PS1‐29 Graph b‐Coloring for Automatic Recognition of Documents Djamel Gaceb, Véronique Eglin, Frank LeBourgeois, Hubert Emptoz
PS1‐30 Fusion of Word Spotting and Spatial Information for Figure Caption Retrieval in Historical Document Images Khurram Khurshid, Claudie Faure, Nicole Vincent
PS1‐31 Segmentation‐free Word Spotting in Historical Printed Documents Basilis Gatos, Ioannis Pratikakis
PS1‐32 Automatic Evaluation Framework for Word Spotting Kengo Terasawa, Hajime Imura, Yuzuru Tanaka
26‐29 July, Barcelona, Spain 52
PS1‐33 FHT: An Unconstraint Farsi Handwritten Text Database Majid Ziaratban, Karim Faez, Fatemeh Bagheri
PS1‐34 HCL2000 ‐ A Large‐scale Handwritten Chinese Character Database for Handwritten Character Recognition Honggang Zhang, Jun Guo, Guang Chen, Chunguang Li
PS1‐35 Compression and String Matching Method for Printed Document Images Hajime Imura, Yuzuru Tanaka
PS1‐36 A Realistic Dataset for Performance Evaluation of Document Layout Analysis Apostolos Antonacopoulos, David Bridson, Christos Papadopoulos, Stefan Pletschacher
PS1‐37 The GERMANA Database Daniel Pérez, Lionel Tarazón, Nicolás Serrano, Francisco Castro, Oriol Ramos Terrades, Alfons Juan
PS1‐38 Trinary Image Mosaicing Based Watermark String Detection Jun Sun, Satoshi Naoi, Yusaku Fujii, Hiroaki Takebe, Yoshinobu Hotta
PS1‐39 A Generic Form Processing Approach for Large Variant Templates Yaakov Navon, Ella Barkan, Boaz Ophir
PS1‐40 Document Binarization Based on Connected Operators Benoit Naegel, Laurent Wendling
PS1‐41 Document Images Restoration by a New Tensor Based Diffusion Process: Application to the Recognition of Old Printed Documents Fadoua Drira, Frank LeBourgeois, Hubert Emptoz
PS1‐42 2D CAD Data Mining Based on Spatial Relation Hiroaki Kizu, Junko Yamamoto, Takeshi Takeda, Keiji Gyohten, Naomichi Sueda
PS1‐43 Keyword Spotting in Document Images through Word Shape Coding Shuyong Bai, Linlin Li, Chew Lim Tan
PS1‐44 Information Retrieval Model for Online Handwritten Script Identification Guo Xian Tan, Christian Viard‐Gaudin, Alex C. Kot
PS1‐45 Detecting Printed and Handwritten Partial Copies of Line Drawings Embedded in Complex Backgrounds Weihan Sun, Koichi Kise
53 ICDAR 2009
PS1‐46 Document Image Retrieval with Local Feature Sequences Jilin Li, Zhi‐Gang Fan, Yadong Wu, Ning Le
PS1‐47 Handwritten Word Image Retrieval with Synthesized Typed Queries José A. Rodríguez‐Serrano, Florent Perronnin
PS1‐48 Generic Feature Selection and Document Processing Hassan Chouaib, Nicole Vincent, Florence Cloppet, Salvator Tabbone
PS1‐49 Scalable Feature Extraction from Noisy Documents Loic Lecerf, Boris Chidlovskii
PS1‐50 A New Block Partitioned Text Feature for Text Verification Xiufei Wang, Lei Huang, Changping Liu
PS1‐51 German Lute Tablature Recognition Christoph Dalitz, Christine Pranzas
PS1‐52 Raster Map Image Analysis Thomas C. Henderson, Trevor Linton
PS1‐53 Information Extraction from Multimodal ECG Documents Fei Wang, Tanveer Syeda‐Mahmood, David Beymer
PS1‐54 A Pixel‐level Statistical Structural Descriptor for Shape Measure and Recognition Jing Zhang, Liu Wenyin
PS1‐55 An A Posteriori Probability Calculation Method for Analytic Word Recognition Applicable to Address Recognition Tomoyuki Hamamura, Takuma Akagi, Bunpei Irie
PS1‐56 Word Image Matching Based on Hausdorff Distances Andrey Andreev, Nikolay Kirov
PS1‐57 A Framework for Adaptation of the Active‐DTW Classifier for Online Handwritten Character Recognition Vandana Roy, Sriganesh Madhvanath, Anand S., Ragunath R. Sharma
PS1‐58 High Performance Chinese/English Mixed OCR with Character Level Language Identification Kai Wang, Jianming Jin, Qingren Wang
26‐29 July, Barcelona, Spain 54
PS1‐59 Arabic Handwriting Recognition Using Restored Stroke Chronology Abdelkarim Elbaati, Houcine Boubaker, Monji Kherallah, Abdellatif Ennaji, Haikal El Abed, Adel M. Alimi
PS1‐60 Combination of Measurement‐Level Classifiers: Output Normalization by Dynamic Time Warping Giuseppe Pirlo, Donato Impedovo, Claudia Adamita Trullo, Erasmo Stasolla
PS1‐61 Statistical Modeling and Learning for Recognition‐Based Handwritten Numeral String Segmentation Yanjie Wang, Xiabi Liu, Yunde Jia
PS1‐62 A New Method for Writer Identification of Handwritten Farsi Documents F. Shahabi, M. Rahmati
PS1‐63 Rearrangement of Recognized Strokes in Online Handwritten Gurmukhi Words Recognition Anuj Sharma, Rajesh Kumar, R.K. Sharma
1600 – 1620 Coffee Break Location: Patio
1620 – 1720 Keynote Lecture 1 Location: Arnau de Vilanova Chair: Apostolos Antonacopoulos (University of Salford)
1620 Mass Digitisation in Digital Libraries: The Experience of the British Library Aly Conteh
1730 – 1850 Session 3.1: Text Line Segmentation Location: Arnau de Vilanova Chair: Hiroshi Sako (Hitachi R&D, Japan)
1730 Markov Random Field Based Text Identification from Annotated Machine Printed Documents Xujun Peng, Srirangaraj Setlur, Venu Govindaraju, Ramachandrula Sitaram, Kiran Bhuvanagiri
1750 A Variational Bayes Method for Handwritten Text Line Segmentation Fei Yin, Cheng‐lin Liu
55 ICDAR 2009
1810 A Unified Framework Based on the Level Set Approach for Segmentation of Unconstrained Double‐Sided Document Images Suffering from Bleed‐Through Reza Farrahi Moghaddam, David Rivest‐Hénault, Itay Bar‐Yosef, Mohamed Cheriet
1830 Script‐Independent Handwritten Textlines Segmentation Using Active Contours Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel
1730 – 1850 Session 3.2: Handwriting Analysis and Recognition ‐ I Location: Lluís Vives I Chair: Cheng‐Lin Liu (Chinese Academy of Sciences, China)
1730 A Novel Rejection Measurement in Handwritten Numeral Recognition Based on Linear Discriminant Analysis Chun Lei He, Louisa Lam, Ching Y. Suen
1750 Indian Multi‐Script Full Pin‐code String Recognition for Postal Automation Umapada Pal, Rami Kumar Roy, Kaushik Roy, Fumitaka Kimura
1810 Bayesian Best‐First Search for Pattern Recognition ‐ Application to Address Recognition Tomoyuki Hamamura, Takuma Akagi, Bunpei Irie
1830 Handling Out‐of‐Vocabulary Words and Recognition Errors Based on Word Linguistic Context for Handwritten Sentence Recognition Solen Quiniou, Mohamed Cheriet, Eric Anquetil
1730 – 1850 Session 3.3: Document Classification Location: Lluís Vives II Chair: Henry S. Baird (Lehigh University, USA)
1730 Pattern Classification on Local Metric Structure Yoshikazu Washizawa
1750 Drop Caps Decomposition for Indexing a New Letter Extraction Method Mickael Coustaty, Jean‐Marc Ogier, Rudolf Pareti, Nicole Vincent
1810 A Rotation Invariant Page Layout Descriptor for Document Classification and Retrieval Albert Gordo, Ernest Valveny
26‐29 July, Barcelona, Spain 56
1830 A Hierarchical Classification Model for Document Categorization Jian‐Wu Xu, Vartika Singh, Venu Govindaraju, Depankar Neogi
Tuesday, July 28th
0900 – 1000 Keynote Lecture 2 Location: Arnau de Vilanova Chair: Umapada Pal (Indian Statistical Institute, India)
0900 Ontology‐Based Document Understanding on the Semantic Desktop Andreas Dengel
1000 – 1020 Coffee Break Location: Patio
1020 – 1200 Session 4.1: Historical Document Analysis Location: Arnau de Vilanova Chair: Simone Marinai (Università di Firenze, Italy)
1020 A Novel Feature Extraction and Classification Methodology for the Recognition of Historical Documents Georgios Vamvakas, Basilis Gatos, Stavros J. Perantoni
1040 Retrieval of the Ornaments from the Hand‐Press Period: An Overview Etienne Baudrier, Sébastien Busson, Silvio Corsini, Mathieu Delalandre, Jérôme Landré, Frédéric Morain‐Nicolier
1100 Word‐Based Adaptive OCR for Historical Books Vladimir Kluzner, Asaf Tzadok, Yuval Shimony, Eugene Walach, Apostolos Antonacopoulos
1120 A New Framework for Recognition of Heavily Degraded Characters in Historical Typewritten Documents Based on Semi‐Supervised Clustering Stefan Pletschacher, Jianying Hu, Apostolos Antonacopoulos
1140 Application of Multi‐Level Classifiers and Clustering for Automatic Word Spotting in Historical Document Images Reza Farrahi Moghaddam, Mohamed Cheriet
57 ICDAR 2009
1020 – 1200 Session 4.2: Online Handwriting Analysis and Recognition – II
Location: Lluís Vives I Chair: Masaki Nakagawa (Tokyo Univ. of Agriculture and Technology, Japan)
1020 Effect of Improved Path Evaluation for On‐line Handwritten Japanese Text Recognition Bilan Zhu, Xiang‐Dong Zhou, Cheng‐Lin Liu, Masaki Nakagawa
1040 Online Handwritten Japanese Character String Recognition Using Conditional Random Fields Xiang‐Dong Zhou, Cheng‐Lin Liu, Masaki Nakagawa
1100 A Study of Feature Design for Online Handwritten Chinese Character Recognition Based on Continuous‐Density Hidden Markov Models Lei Ma, Qiang Huo, Yu Shi
1120 An Investigation of Imaginary Stroke Techinique for Cursive Online Handwriting Chinese Character Recognition Kai Ding, Guoqiang Deng, Lianwen Jin
1200 A Character‐Structure‐Guided Approach to Estimating Possible Orientations of a Rotated Isolated Online Handwritten Chinese Character Tingting He, Qiang Huo
1020 – 1200 Session 4.3: Document Image Processing and Enhancement
Location: Lluís Vives II Chair: David Doermann (University of Maryland, USA)
1020 Threshold Correction of Document Image Binarization for Ruled‐line Extraction Hiroshi Tanaka
1040 Registration and Enhancement of Double‐Sided Degraded Manuscripts Acquired in Multispectral Modality Anna Tonazzini, Gianfranco Bianco, Emanuele Salerno
1100 Document Image Binarisation Using Markov Field Model Thibault Lelore, Frédéric Bouchara
26‐29 July, Barcelona, Spain 58
1120 Clutter Noise Removal in Binary Document Images Mudit Agrawal, David Doermann
1140 Robust Color Image Enhancement of Digitized Books Jian Fan
1210 – 1330 Session 5.1: Character Recognition Location: Arnau de Vilanova Chair: George Nagy (Rensselaer Polytechnic Institute, Troy, USA)
1210 Robust Recognition of Documents by Fusing Results of Word Clusters Venkat Rasagna, Anand Kumar, C.V. Jawahar, R. Manmatha
1230 Learning on the Fly: Font‐Free Approaches to Difficult OCR Problems Andrew Kae, Erik Learned‐Miller
1250 Low Cost Correction of OCR Errors Using Learning in a Multi‐Engine Environment Ahmad Abdulkader, Mathew R. Casey
1310 Error‐Correcting Output Coding for the Convolutional Neural Network for Optical Character Recognition Huiqun Deng, George Stathopoulos, Ching Y. Suen
1210 – 1330 Session 5.2: Arabic Handwriting Character Recognition Location: Lluís Vives I Chair: Volker Märgner (Technische Universitaet Braunschweig, Germany)
1210 Isolated Handwritten Farsi Numerals Recognition Using Sparse and Over‐Complete Representations W.M. Pan, T.D. Bui, C.Y. Suen
1230 Arabic and Latin Script Identification in Printed and Handwritten Types Based on Steerable Pyramid Features Mohamed Benjelil, Slim Kanoun, Rémy Mullot, Adel M. Alimi
1250 Confidence‐Based Discriminative Training for Model Adaptation in Offline Arabic Handwriting Recognition Philippe Dreuw, Georg Heigold, Hermann Ney
59 ICDAR 2009
1310 Fine Classification of Unconstrained Handwritten Persian/Arabic Numerals by Removing Confusion amongst Similar Classes Alireza Alaei, P. Nagabhushan, Umapada Pal
1210 – 1330 Session 5.3: Document Retrieval Location: Lluís Vives II Chair: Daniel Lopresti (Lehigh University, USA)
1210 Logo Matching for Document Image Retrieval Guangyu Zhu, David Doermann
1230 Bayesian Similarity Model Estimation for Approximate Recognized Text Search Atsuhiro Takasu
1250 Finding the Most Probable Ranking of Objects with Probabilistic Pairwise Preferences Mikhail Parakhin, Patrick Haluptzok
1310 Google Newspaper Search – Image Processing and Analysis Pipeline Krishnendu Chaudhury, Ankur Jain, Sriram Thirthala, Vivek Sahasranaman, Shobhit Saxena, Selvam Mahalingam
1330 – 1430 Lunch Location: Martí Franqués
1330 – 1430 TC10 / TC11 Meeting Location: Lluís Vives II
1430 – 1600 Poster Session II Location: Arnau de Vilanova
PS2‐1 Handwritten Text Line Segmentation by Shredding Text into its Lines Anguelos Nicolaou, Basilis Gatos
PS2‐2 User‐Guided Wrapping of PDF Documents Using Graph Matching Techniques Tamir Hassan
PS2‐3 Handwritten Text Line Identification in Indian Scripts Bidyut Baran Chaudhuri, Sumedha Bera
PS2‐4 Classifying Foreground Pixels in Document Images Prateek Sarkar, Eric Saund, Jing Lin
26‐29 July, Barcelona, Spain 60
PS2‐5 PixLabeler: User Interface for Pixel‐Level Labeling of Elements in Document Images Eric Saund, Jing Lin, Prateek Sarkar
PS2‐6 Text Line Segmentation Based on Morphology and Histogram Projection Rodolfo P. dos Santos, Gabriela S. Clemente, Tsang Ing Ren, George D.C. Cavalcanti
PS2‐7 A Self‐Adaptive Method for Extraction of Document‐Specific Alphabets Stefan Pletschacher
PS2‐8 Affixal Approach versus Analytical Approach for Off‐Line Arabic Decomposable Vocabulary Recognition Slim Kanoun, Fouad Slimane, Hanêne Guesmi, Rolf Ingold, Adel M. Alimi, Jean Hennebert
PS2‐9 Evaluation of Different Strategies to Optimize an HMM‐Based Character Recognition System Murilo Santos, Albert Ko, Luis S. Oliveira, Robert Sabourin, Alessandro L. Koerich, Alceu S. Britto Jr.
PS2‐10 An Open Source Tesseract Based Optical Character Recognizer for Bangla Script Md. Abul Hasnat, Muttakinur Rahman Chowdhury, Mumit Khan
PS2‐11 Character Recognition under Severe Perspective Distortion Peng Zhou, Linlin Li, Chew Lim Tan
PS2‐12 Vector Representation of Graphs: Application to the Classification of Symbols and Letters Nicolas Sidère, Pierre Héroux, Jean‐Yves Ramel
PS2‐13 A Novel Two Stage Evaluation Methodology for Word Segmentation Techniques Georgios Louloudis, Nikolaos Stamatopoulos, Basilis Gatos
PS2‐14 Invariant Primitives for Handwritten Arabic Script: A Contrastive Study of Four Feature Sets Sofiene Haboubi, Samia Maddouri, Noureddine Ellouze, Hailkal El‐Abed
PS2‐15 Scaling Up Whole‐Book Recognition Pingping Xiu, Henry Baird
61 ICDAR 2009
PS2‐16 Semi‐automatic Forensic Reconstruction of Ripped‐up Documents Patrick De Smet
PS2‐17 A Symbol Spotting Approach Based on the Vector Model and a Visual Vocabulary Thi‐Oanh Nguyen, Salvatore Tabbone, Alain Boucher
PS2‐18 A Feedback‐Based Multi‐Classifier System Giuseppe Pirlo, Claudia Adamita Trullo, Donato Impedovo
PS2‐19 Machine Authentication of Security Documents Utpal Garain, Biswajit Halder
PS2‐20 Semi‐automatic Roof Reconstruction Tong Lu, Yubin Yang, Feng Su, Zhengxing Sun
PS2‐21 Robustness of Signature Verification Systems to Imitators with Increasing Skills Fernando Alonso‐Fernandez, Julian Fierrez, Almudena Gilperez, Javier Galbally, Javier Ortega‐Garcia
PS2‐22 Document Analysis Support for the Manual Auditing of Elections Daniel Lopresti, Xiang Zhou, Xiaolei Huang, Gang Tan
PS2‐23 Constant‐Time Locally Optimal Adaptive Binarization Iuliu Konya, Christoph Seibert, Stefan Eickeler, Sebastian Glahn
PS2‐24 Enhanced Text Extraction from Arabic Degraded Document Images Using EM Algorithm Wafa Boussellaa, Aymen Bougacha, Abderrazak Zahour, Haikal El Abed, Adel Alimi
PS2‐25 Feature Based Binarization of Document Images Degraded by Uneven Light Condition Jung Gap Kuk, Nam Ik Cho
PS2‐26 Manuscript Bleed‐through Removal via Hysteresis Thresholding Rolando Estrada, Carlo Tomasi
PS2‐27 Pre‐Processing of Degraded Printed Documents by Non‐local Means and Total Variation Laurence Likforman‐Sulem, Jérôme Darbon, Elisa H. Barney Smith
26‐29 July, Barcelona, Spain 62
PS2‐28 Character‐SIFT: A Novel Feature for Offline Handwritten Chinese Character Recognition Zhiyi Zhang, Lianwen Jin, Kai Ding, Xue Gao
PS2‐29 Page Rule‐Line Removal Using Linear Subspaces in Monochromatic Handwritten Arabic Documents Wael Abd‐Almageed, Jayant Kumar, David Doermann
PS2‐30 Improvements in BBN’s HMM‐Based Offline Arabic Handwriting Recognition System Shirin Saleem, Huaigu Cao, Krishna Subramanian, Matin Kamali, Rohit Prasad, Prem Natarajan
PS2‐31 New Algorithm of Straight or Curved Baseline Detection for Short Arabic Handwritten Writing Houcine Boubaker, Monji Kherallah, Adel M. Alimi
PS2‐32 HMM Based Handwritten Word Recognition System by Using Singularities Sebastiano Impedovo, Anna Ferrante, Raffaele Modugno
PS2‐33 Shape Encoded Post Processing of Gurmukhi OCR Dharam Veer Sharma, Gurpreet Singh Lehal, Sarita Mehta
PS2‐34 Segmentation of Arabic Handwriting Based on both Contour and Skeleton Segmentation Safwan Wshah, Zhixin Shi, Venu Govindaraju
PS2‐35 A Kai Style Calligraphic Beautification Method for Handwriting Chinese Character Weiping Xia, Lianwen Jin
PS2‐36 Stochastic Model of Stroke Order Variation Yoshinori Katayama, Seiichi Uchida, Hiroaki Sakoe
PS2‐37 Recognition of Handwritten Numerical Fields in a Large Single‐Writer Historical Collection Marius Bulacu, Axel Brink, Tijn van der Zant, Lambert Schomaker
PS2‐38 Spatial and Spectral Based Segmentation of Text in Multispectral Images of Ancient Documents Martin Lettner, Robert Sablatnig
63 ICDAR 2009
PS2‐39 Revealing the Visually Unknown in Ancient Manuscripts with a Similarity Measure for IR‐Imaged Inks Aaron Licata, Alexandra Psarrou, Vassiliki Kokla
PS2‐40 Italic or Roman: Word Style Recognition without A Priori Knowledge for Old Printed Documents Loris Eynard, Hubert Emptoz
PS2‐41 Restoration and Segmentation of Highly Degraded Characters Using a Shape‐Independent Level Set Approach and Multi‐level Classifiers Reza Farrahi Moghaddam, David Rivest‐Henault, Mohamed Cheriet
PS2‐42 Steerable Pyramid Based Complex Documents Images Segmentation Mohamed Benjelil, Slim Kanoun, Rémy Mullot, Adel M. Alimi
PS2‐43 A Method for Automatically Extracting Road Layers from Raster Maps Yao‐Yi Chiang, Craig A. Knoblock
PS2‐44 Learning Rich Hidden Markov Models in Document Analysis: Table Location Ana Costa e Silva
PS2‐45 Seizing the Treasure: Transferring Knowledge in Invoice Analysis Frederick Schulz, Markus Ebbecke, Michael Gillmann, Benjamin Adrian, Stefan Agne, Andreas Dengel
PS2‐46 Unconstrained Handwritten Document Layout Extraction Using 2D Conditional Random Fields Florent Montreuil, Emmanuèle Grosicki, Laurent Heutte, Stéphane Nicolas
PS2‐ 47 “The Godfather” vs. “Chaos”: Comparing Linguistic Analysis Based on On‐line Knowledge Sources and Bags‐of‐N‐Grams for Movie Review Valence Estimation Björn Schuller, Joachim Schenk, Gerhard Rigoll, Tobias Knaup
PS2‐48 Improvements in Keyword Search Japanese Characters within Handwritten Digital Ink Cheng Cheng, Bilan Zhu, Xiaorong Chen, Masaki Nakagawa
PS2‐49 Hierarchical On‐line Arabic Handwriting Recognition Raid Saabni, Jihad El‐Sana
PS2‐50 Pen Acoustic Emissions for Text and Gesture Recognition Andrew Seniuk, Dorothea Blostein
26‐29 July, Barcelona, Spain 64
PS2‐51 GMs in On‐Line Handwritten Whiteboard Note Recognition: The Influence of Implementation and Modeling Joachim Schenk, Benedikt Hörnler, Björn Schuller, Artur Braun, Gerhard Rigoll
PS2‐52 Using top n Recognition Candidates to Categorize On‐line Handwritten Documents Sebastián Peña Saldarriaga, Emmanuel Morin, Christian Viard‐Gaudin
PS2‐53 Recognition‐Based Segmentation Algorithm for On‐Line Arabic Handwriting Khaled Daifallah, Nizar Zarka, Hassan Jamous
PS2‐54 A Framework Based on Semi‐Supervised Clustering for Discovering Unique Writing Styles Bharath A., Sriganesh Madhvanath
PS2‐55 Embedded Bernoulli Mixture HMMs for Handwritten Word Recognition Adrià Giménez, Alfons Juan
PS2‐56 A Collaborative Interface for Multimodal Ink and Audio Documents Amit Regmi, Stephen M. Watt
PS2‐57 PDF‐TREX: An Approach for Recognizing and Extracting Tables from PDF Documents Ermelinda Oro, Massimo Ruffolo
PS2‐58 Analysis of Book Documents’ Table of Content Based on Clustering Liangcai Gao, Zhi Tang, Xiaofan Lin, Xin Tao, Yimin Chu
PS2‐59 An RDF‐Based Blackboard Architecture for Improving Table Analysis Vanessa Long
PS2‐60 Extraction of Nom Text Regions from Stele Images Using Area Voronoi Diagram Thai V. Hoang, Salvatore Tabbone, Ngoc‐Yen Pham
PS2‐61 Two‐stage Approach for Word‐wise Script Identification Sukalpa Chanda, Srikanta Pal, Katrin Franke, Umapada Pal
PS2‐62 Online Text‐independent Writer Identification Based on Temporal Sequence and Shape Codes Bangy Li, Tieniu Tan
PS2‐63 Author Identification Using Compression Models D. Pavelec, L.S. Oliveira, E. Justino, F.D. Nobre Neto, L.V. Batista
65 ICDAR 2009
1600 – 1620 Coffee Break Location: Patio
1620 – 1720 Keynote Lecture 3 Location: Arnau de Vilanova Chair: Josep Lladós (Computer Vision Centre, Spain)
1620 Enterprise Approach to OCR Technology Development Andrey Isaev
1730 – 1850 Session 6.1: Performance Evaluation and Ground‐truthing
Location: Arnau de Vilanova Chair: Jean‐Marc Ogier (L3i Laboratory, La Rochelle, France)
1730 Results of the RIMES Evaluation Campaign for Handwritten Mail Processing Emmanuèle Grosicki, Matthieu Carré, Jean‐Marie Brodin, Edouard Geoffrois
1750 A New Arabic Printed Text Image Database and Evaluation Protocols Fouad Slimane, Rolf Ingold, Slim Kanoun, Adel M. Alimi, Jean Hennebert
1810 A Tool for Ground‐Truthing Text Lines and Characters in Off‐Line Handwritten Chinese Documents Fei Yin, Qiu‐feng Wang, Cheng‐lin Liu
1830 A Methodology for Document Image Dewarping Techniques Performance Evaluation Nikolaos Stamatopoulos, Basilis Gatos, Ioannis Pratikakis
1730 – 1850 Session 6.2: Statistical Classifier‐Based Handwriting Recognition
Location: Lluís Vives I Chair: Louisa Lam (Concordia University, USA)
1730 HMM‐Based Handwritten Amharic Word Recognition with Feature Concatenation Yaregal Assabie, Josef Bigun
1750 Learning Bayesian Networks by Evolution for Classifier Combination Claudio De Stefano, Francesco Fontanella, Alessandra Scotto di Freca, Angelo Marcelli
26‐29 July, Barcelona, Spain 66
1810 Stochastic Segment Modeling for Offline Handwriting Recognition Prem Natarajan, Krishna Subramanian, Anurag Bhardwaj, Rohit Prasad
1830 Maximum Margin Training of Gaussian HMMs for Handwriting Recognition Trinh‐Minh‐Tri Do, Thierry Artières
1730 – 1850 Session 6.3: Writer Identification and Verification Location: Lluís Vives II Chair: Sargur Srihari (University at Buffalo, USA)
1730 A Set of Chain Code Based Features for Writer Recognition Imran Siddiqi, Nicole Vincent
1750 Hierarchical Shape Primitive Features for Online Text‐independent Writer Identification Bangy Li, Zhenan Sun, Tieniu Tan
1810 Off‐Line Multi‐Script Writer Identification Using AR Coefficients Utpal Garain, Thierry Paquet
1830 On the Use of Textural Features for Writer Identification in Old Handwritten Music Scores Alicia Fornés, Josep Lladós, Gemma Sánchez, Horst Bunke
1930 – 2400 Conference Banquet Location: Sala Maremagnum (Barcelona city centre)
Wednesday, July 29th
0900 – 1000 Keynote Lecture 4 Location: Arnau de Vilanova Chair: Mohamed Cheriet (École de Technologie Supérieure, Canada)
0900 Ten editions of ICDAR: Overview and Outlook Guy Lorette
1000 – 1020 Coffee Break Location: Patio
67 ICDAR 2009
1020 – 1140 Session 7.1: Page Segmentation and Layout Analysis Location: Arnau de Vilanova Chair: Basilis Gatos (National Centre for Scientific Research, Greece)
1020 Text Lines and Snippets Extraction for 19th Century Handwriting Documents Layout Analysis Vincent Malleron, Véronique Eglin, Hubert Emptoz, Stéphanie Dord‐Crouslé, Philippe Régnier
1040 Improving the Table Boundary Detection in PDFs by Fixing the Sequence Error of the Sparse Lines Ying Liu, Kun Bai, Prasenjit Mitra, C. Lee Giles
1100 Voronoi++: A Dynamic Page Segmentation Approach Based on Voronoi and Docstrum Features Mudit Agrawal, David Doermann
1120 Context‐oriented Layout Optimization of Large‐Print Textbooks Itaru Tatsumi, Hitoshi Habe, Masatsugu Kidode
1020 – 1140 Session 7.2: Handwriting Analysis and Recognition – II Location: Lluís Vives I Chair: Jin H. Kim (Advanced Institute of Science and Technology, Korea)
1020 Prototype Selection for Handwritten Connected Digits Classification Cristiano de Santana Pereira, George D.C. Cavalcanti
1040 Recognition of Handwritten Chinese Characters by Combining Regularization, Fisher's Discriminant and Distorted Sample Generation K.C. Leung, C.H. Leung
1100 From Isolated Handwritten Characters to Fields Recognition: There’s Many a Slip Twixt Cup and Lip Christopher Kermorvant, Anne‐Laure Bianne, Patrick Marty, Farès Menasri
1120 Integrating Language Model in Handwritten Chinese Text Recognition Qiu‐Feng Wang, Fei Yin, Cheng‐Lin Liu
26‐29 July, Barcelona, Spain 68
1020 – 1140 Session 7.3: Scientific Document Recognition Location: Lluís Vives II Chair: Dorothea Blostein (Queen’s University, Ontario, Canada)
1020 Mathematical Symbol Indexing Using Topologically Ordered Clusters of Shape Contexts Simone Marinai, Beatrice Miotti, Giovanni Soda
1040 Towards Handwritten Mathematical Expression Recognition Ahmad‐Montaser Awal, Harold Mouchère, Christian Viard‐Gaudin
1100 Utilizing Consistency Context for Handwritten Mathematical Expression Recognition Kang Kim, Taik Heon Rhee, Jae Seung Lee, Jin Hyung Kim
1120 The Understanding and Structure Analyzing for Online Handwritten Chemical Formulas Xin Wang, Guangshun Shi, Jufeng Yang
1150 – 1320 Poster Session III Location: Arnau de Vilanova
PS3‐1 A Survey of Techniques for Document and Archaeology Artefact Reconstruction Florian Kleber, Robert Sablatnig
PS3‐2 A New Approach for Skew Correction of Documents Based on Particle Swarm Optimization Javad Sadri, Mohamed Cheriet
PS3‐3 New Trends in Digital Scanning Processes Sebastiano Impedovo, Raffaele Modugno, Anna Ferrante, Erasmo Stasolla
PS3‐4 Document Content Extraction Using Automatically Discovered Features Sui‐Yu Wang, Henry Baird, Chang An
PS3‐5 Graphological Analysis of Handwritten Text Documents for Human Resources Recruitment Ricard Coll, Alicia Fornés, Josep Lladós
PS3‐6 Using Kernel Density Classifier with Topic Model and Cost Sensitive Learning for Automatic Text Categorization Dwi Sianto Mansjur, Ted S. Wada, Biing Hwang Juang
69 ICDAR 2009
PS3‐7 Unsupervised HMM Adaptation Using Page Style Clustering Huaigu Cao, Rohit Prasad, Shirin Saleem, Premkumar Natarajan
PS3‐8 Finding Images and Line‐Drawings in Document‐Scanning Systems Shumeet Baluja, Michele Covell
PS3‐9 Detection of Incoherences in a Document Corpus Based on the Application of a Neuro‐Fuzzy System Susana Martín, Víctor Arribas, Gregorio I. Sáinz
PS3‐10 Image Classification to Improve Printing Quality of Mixed‐Type Documents Rafael Dueire Lins, Gabriel Pereira e Silva, Steven J. Simske, Jian Fan, Mark Shaw, Paulo Sá, Marcelo Thielo
PS3‐11 Comparative Study of Devnagari Handwritten Character Recognition Using Different Feature and Classifiers Umapada Pal, Tetsushi Wakabayashi, Fumitaka Kimura
PS3‐12 Temporal Order Recovery of the Scanned Handwriting Abdelkarim Elbaati, Monji Kherallah, Abdellatif Ennaji, Adel M. Alimi
PS3‐13 Explicit Fuzzy Modeling of Shapes and Positioning for Handwritten Chinese Character Recognition Adrien Delaye, Eric Anquetil, Sébastien Macé
PS3‐14 Rejection Strategies with Multiple Classifiers for Handwritten Character Recognition Xu‐Cheng Yin, Hong‐Wei Hao, Yun‐Feng Tang, Jun Sun, Satoshi Naoi
PS3‐15 A New Method for Rotation Free Method for Online Unconstrained Handwritten Chinese Word Recognition: A Holistic Approach Kai Ding, Lianwen Jin, Xue Gao
PS3‐16 A Novel Approach for Rotation Free Online Handwritten Chinese Character Recognition Shengming Huang, Lianwen Jin, Jin Lv
PS3‐17 Hierarchical Decomposition of Handwriting Deformation Vector Field Using 2D Warping and Global/Local Affine Transformation Toru Wakahara, Seiichi Uchida
PS3‐18 Recurrent HMMs and Cursive Handwriting Recognition Graphs Marc‐Peter Schambach
26‐29 July, Barcelona, Spain 70
PS3‐19 Unsupervised Selection and Discriminative Estimation of Orthogonal Gaussian Mixture Models for Handwritten Digit Recognition Xuefeng Chen, Xiabi Liu, Yunde Jia
PS3‐20 Writer Adaptation for Online Handwriting Recognition System Using Virtual Examples Hidetoshi Miyao, Minoru Maruyama
PS3‐21 Line Segmentation for Degraded Handwritten Historical Documents Itay Bar‐Yosef, Nate Hagbi, Klara Kedem, Itshak Dinstein
PS3‐22 A Dual Taxonomy for Defects in Digitized Historical Photos Edoardo Ardizzone, A. De Polo, Haris Dindo, Giuseppe Mazzola, C. Nanni
PS3‐23 A Modified Adaptive Logical Level Binarization Technique for Historical Document Images Konstantinos Ntirogiannis, Basilis Gatos, Ioannis Pratikakis
PS3‐24 Automatic Corresponding Control Points Selection for Historical Document Image Registration Jie Wang, Michael S. Brown, Chew Lim Tan
PS3‐25 How to Improve a Handwriting Recognition System Haikal El Abed, Volker Märgner
PS3‐26 Combining Alignment Results for Historical Handwritten Document Analysis Emanuel Indermühle, Marcus Liwicki, Horst Bunke
PS3‐27 Separate Chinese Character and English Character by Cascade Classifier and Feature Selection Yuanping Zhu, Jun Sun, Akihiro Minagawa, Yoshinobu Hotta, Satoshi Naoi
PS3‐28 A Multi‐Lingual Recognition System for Arabic and Latin Handwriting Yousri Kessentini, Thierry Paquet, AbdelMajid Ben Hamadou
PS3‐29 Modeling, Classifying and Annotating Weakly Annotated Images Using Bayesian Network Sabine Barrat, Salvatore Tabbone
PS3‐30 CASIA‐OLHWDB1: A Database of Online Handwritten Chinese Characters Da‐Han Wang, Cheng‐Lin Liu, Jin‐Lun Yu, Xiang‐Dong Zhou
PS3‐31 Recognition of On‐Line Handwritten Commutative Diagrams Andreas Stoffel, Ernesto Tapia, Raúl Rojas
71 ICDAR 2009
PS3‐32 An Improved Online Tamil Character Recognition Engine Using Post‐Processing Methods Suresh Sundaram, Angarai Ganesan Ramakrishnan
PS3‐33 PENTOOLS ‐ A MATLAB Toolkit for On‐line Pen‐Based Data Experimentation Richard M. Guest
PS3‐34 Affine Distortion Compensation for an Isolated Online Handwritten Chinese Character Using Combined Orientation Estimation and HMM‐Based Minimax Classification Tingting He, Qiang Huo
PS3‐35 Efficient Generation of Comprehensive Database for Online Arabic Script Recognition Raid Saabni, Jihad El‐Sana
PS3‐36 Capturing Digital Ink as Retrieving Fragments of Document Images Kazumasa Iwata, Koichi Kise, Tomohiro Nakai, Masakazu Iwamura, Seiichi Uchida, Shinichiro Omachi
PS3‐37 A Probabilistic Framework for Soft Target Learning in Online Cursive Handwriting Recognition Xiaoyuan Zhu, Yong Ge, Fengjun Guo, Lixin Zhen
PS3‐38 Selecting Features in On‐Line Handwritten Whiteboard Note Recognition: SFS or SFFS? Joachim Schenk, Moritz Kaiser, Gerhard Rigoll
PS3‐39 HMM‐Based Online Recognition of Handwritten Chemical Symbols Yang Zhang, Guangshun Shi, Jufeng Yang
PS3‐40 Improving a DTW‐Based Recognition Engine for On‐line Handwritten Characters by Using MLPs María José Castro‐Bleda, Salvador España‐Boquera, Jorge Gorbe‐Moya, Francisco Zamora‐Martínez, David Llorens‐Piñana, Andrés Marzal‐Varó, Federico Prat‐Villar, Juan Miguel Vilar‐Torres
PS3‐41 Online Recognition of Multi‐Stroke Symbols with Orthogonal Series Oleg Golubitsky, Stephen M. Watt
PS3‐42 Development and Evaluation of Text Localization Techniques Based on Structural Texture Features and Neural Classifiers Christos Emmanouilidis, Costas Batsalas, Nikos Papamarkos
26‐29 July, Barcelona, Spain 72
PS3‐43 Automated Ground Truth Data Generation for Newspaper Document Images Thomas Strecker, Joost van Beusekom, Sahin Albayrak, Thomas M. Breuel
PS3‐44 Robust Extraction of Text from Camera Images Shyama Prosad Chowdhury, Soumyadeep Dhar, Amit Kumar Das, Bhabatosh Chanda, Karen McMenemy
PS3‐45 A Robust Wavelet Transform Based Technique for Video Text Detection Palaiahnakote Shivakumara, Trung Quy Phan, Chew Lim Tan
PS3‐46 Disease‐Specific Extraction of Text from Cardiac Echo Videos for Decision Support Tanveer Syeda‐Mahmood, David Beymer, Arnon Amir
PS3‐47 Improving the Enrollment in Dynamic Signature Verfication with Synthetic Samples Javier Galbally, Julian Fierrez, Marcos Martinez‐Diaz, Javier Ortega‐Garcia
PS3‐48 Global Features for the Off‐Line Signature Verification Problem Vu Nguyen, Michael Blumenstein, Graham Leedham
PS3‐49 An Investigation of Predictive Profiling from Handwritten Signature Data Michael C. Fairhurst, Márjory Cristiany Da Costa Abreu
PS3‐50 Capturing Reliable Data for Computer‐Based Forensic Handwriting Analysis II: Pen‐position Activations Katrin Franke
PS3‐51 A Multi‐Hypothesis Approach for Off‐Line Signature Verification with HMMs Luana Batista, Eric Granger, Robert Sabourin
PS3‐52 Symbol Detection Using Region Adjacency Graphs and Integer Linear Programming Pierre Le Bodic, Hervé Locteau, Sébastien Adam, Pierre Héroux, Yves Lecourtier, Arnaud Knippel
PS3‐53 Graphic Symbol Recognition Using Graph Based Signature and Bayesian Network Classifier Muhammad Muzzamil Luqman, Thierry Brouard, Jean‐Yves Ramel
PS3‐54 Inductive Logic Programming for Symbol Recognition K.C. Santosh, Bart Lamiroy, Jean‐Philippe Ropers
73 ICDAR 2009
PS3‐55 Logo Detection in Document Images Based on Boundary Extension of Feature Rectangles Hongye Wang, Youbin Chen
PS3‐56 Identification of Mathematical Expressions in Document Images Utpal Garain
PS3‐57 A Unified Framework for Recognizing Handwritten Chemical Expressions Ming Chang, Shi Han, Dongmei Zhang
PS3‐58 Statistical Classification of Spatial Relationships among Mathematical Symbols Walaa Aly, Seiichi Uchida, Akio Fujiyoshi, Masakazu Suzuki
PS3‐59 Issues in Performance Evaluation: A Case Study of Math Recognition Adrien Lapointe, Dorothea Blostein
PS3‐60 Syntactic Detection and Correction of Misrecognitions in Mathematical OCR Akio Fujiyoshi, Masakazu Suzuki, Seiichi Uchida
PS3‐61 Extraction of Characters on Signboards in Natural Scene Images by Stump Classifiers Minoru Maruyama, Takuma Yamaguchi
1330 – 1430 Lunch Location: Martí Franqués
1430 – 1550 Panel Session Location: Arnau de Vilanova Chair: Horst Bunke (University of Bern, Switzerland)
1430 Current Trends and Future Challenges in Document Image Analysis
1600 – 1620 Coffee Break Location: Patio
26‐29 July, Barcelona, Spain 74
1620 – 1750 Competition Session Location: Arnau de Vilanova Chair: Wenyin Liu (City University of Hong Kong, China) Ernest Valveny (Computer Vision Centre, Spain)
1620 ICDAR 2009 Page Segmentation Competition Apostolos Antonacopoulos, Stefan Pletschacher, David Bridson, Christos Papadopoulos
1630 ICDAR 2009 Document Image Binarization Contest (DIBCO 2009) Basilis Gatos, Konstantinos Ntirogiannis, Ioannis Pratikakis
1640 ICDAR 2009 Arabic Handwriting Recognition Competition Volker Märgner, Haikal El Abed
1650 ICDAR 2009 Online Arabic Handwriting Recognition Competition Haikal El Abed, Volker Märgner, Monji Kherallah, Adel M. Alimi
1700 ICDAR 2009 Handwriting Segmentation Contest Basilis Gatos, Nikolaos Stamatopoulos, Georgios Louloudis
1710 ICDAR 2009 Handwriting Recognition Competition Emmanuèle Grosicki, Haikal El Abed
1720 ICDAR 2009 Signature Verification Competition Vivian L. Blankers, C. Elisa van den Heuvel, Katrin Y. Franke, Louis G. Vuurpijl
1730 ICDAR 2009 Book Structure Extraction Competition Antoine Doucet, Gabriella Kazai, Bodin Dresevic, Aleksandar Uzelac, Bogdan Radakovic, Nikola Todic
1740 ICDAR 2009 Handwritten Farsi/Arabic Character Recognition Competition Saeed Mozaffari, Hadi Soltanizadeh
1800 – 1830 Awards Presentation / Closing Session Location: Arnau de Vilanova
75 ICDAR 2009
Phrasebook
English Català Español
Hello / Hi Hola Hola How are you? Què tal? ¿Qué tal? Very well, thank you Molt bé, gràcies Muy bien, gracias Yes / No Sí / No Sí / No Please Si us plau Por favor Excuse me Perdoni Disculpe I’m sorry Ho sento Lo siento Goodbye Adéu Adiós Goodnight Bona nit Buenas noches Morning / Afternoon / Evening
Matí / Tarda / Vespre Mañana / Tarde / Anochecer
Yesterday / Today / Tomorrow
Ahir / Avui / Demà Ayer / Hoy / Mañana
Here / There Aquí / Allà Aquí / Allí Pleased to meet you Molt de gust Un placer conocerte See you soon Fins aviat Hasta pronto That’s fine Està bé Está bien Where is the “Serhs Campus” hotel?
On és l’hotel “Serhs Campus”?
¿Dónde está el hotel “Serhs Campus”?
How can I go to the “Cerdanyola‐UAB” train station?
Per on es va a l’estació de tren de “Cerdanyola‐UAB”?
¿Por dónde se va a la estación de tren de “Cerdanyola‐UAB”?
Do you speak English? Parles anglès? ¿Hablas inglés? I don’t understand No l’entenc No lo entiendo Could you speak more slowly?
Pot parlar més a poc a poc?
Puede hablar más lentamente?
Where can I connect my laptop?
On puc connectar el meu portàtil?
¿Dónde puedo conectar mi portátil?
May I introduce you to… Li presento a… Le presento a...
26‐29 July, Barcelona, Spain 76
English Català Español
What’s your name? Com et dius? ¿Como te llamas? Where is the toilet? On és el bany? ¿Dónde está el baño? Where can I take the bus A3 from?
On puc prendre l’autobús A3?
¿Dónde puedo tomar el autobús A3?
Left / Right Esquerra / Dreta Izquierda / Derecha Is there a chemist’s nearby?
Hi ha cap farmàcia a prop?
¿Hay alguna farmacia cerca?
Where can I take a taxi from?
On puc agafar un taxi? ¿Dónde puedo tomar un taxi?
I would like to rent a car Voldria llogar un cotxe. Quisiera alquilar un coche Big / Small More / Less
Gran / Petit Més / Menys
Grande / Pequeño Más / Menos
Where is the “Arnau de Vilanova” conference room?
On és la sala de conferències “Arnau de Vilanova”?
¿Dónde está la sala de conferencias “Arnau de Vilanova”?
How far is it to…? Quant hi ha fins…? ¿Cuánto hay hasta…? Glass of water Got d’aigua Vaso de agua
Tourist information office Oficina d’informació turística
Oficina de información turística
Coffee Cafè Café Where is the nearest metro station?
On és l’estació de metro més propera?
¿Dónde está la estación de metro más cercana?
How much does this T‐Shirt cost?
Quant costa aquesta samarreta?
¿Cuando cuesta esta camiseta?
Too expensive / cheap Massa car / barat Demasiado caro / barato
0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10 Zero, un, dos, tres, quatre, cinc, sis, set, vuit, nou, deu
Cero, uno, dos, tres, cuatro, cinco, seis, siete, ocho, nueve, diez
Can I have a receipt? Em pot donar el tiquet? ¿Me puede dar el tiquet?
77 ICDAR 2009
Conference Statistics Overall 430 submissions were received for ICDAR 2009, out of which 87 (20%) were selected as oral presentations and 190 (44%) as poster presentations. The statistics per topic are shown below. Please note that each paper may have more than one keywords specified, so the graph below is only indicative.
Multim
edia D
ocum
ents
Colour-
base
d DIA
Table an
d form
analys
is
Multilin
gual
docu
ments
Writer Id
entifi
catio
n
Signatu
re Veri
ficati
on
Docum
ent E
ngine
ering
Text/G
raphic
s Sep
aratio
n
Graphic
s Rec
ognit
ion
Camera
and V
ideo D
IA
Pen-ba
sed C
ompu
ting
Docum
ent C
lassif
icatio
n
Symbo
l Rec
ognit
ion
Docum
ent D
B and D
L
Perform
ance
Evalua
tion
Method
ologies
Docum
ent R
etriev
al
Layo
ut Analy
sis
Docum
ent U
nderst
andin
g
Histori
cal D
ocum
ents
Doc. Im
age P
rocess
ing
Text S
egm. a
nd Extr
action
Featur
e Extr
actio
n
DIA Sys
tems a
nd Appli
catio
ns
Charac
ter R
ecogn
ition
Handw
riting
Rec
ognit
ion
0
20
40
60
80
100
120
140
160
180
Keyword Counts
AcceptedSubmitted
Submissions per Continent
145
179
222
25
57
Africa Asia Europe North America South America Oceania
26‐29 July, Barcelona, Spain 78
Notes
ICDAR 2009 is sponsored by TC10 (Graphics Recognition) and TC11 (Reading Systems) of the International Association of Pattern Recognition (IAPR) and by
the following organisations: