22 - 25 may, 2017 marrakesh | morocco … · taifi khaddouj, ahdid rachid, fakir mohamed, safi...
TRANSCRIPT
| Cadi Ayyad University | Marrakesh | Morocco |
© "Totality" - Jing Ziou
© Anna Chupa & Michael Chupa
The Book Abstracts
CGiV2017 – 14th Computer Graphics, Imaging and Visualization
22 - 25 May, 2017
| Cadi Ayyad University | Marrakesh | Morocco |
www.graphicslink.co.uk/cgiv2017/
CGiV2017 Forum
© Chris R Kitchener
iV2017 & CGiV2017 | DIGITAL ART GALLERY Online Exhibition July 2017- June 2018
V I R T U A L G A L L E R Y V E N U E
www.g raph ic s l i nk .c o .uk /DART.h tm
Exhibiting Artists:
Anna Chupa
Bogdan Soban
Bruce Wands
Chris R Kitchener
Corinne Whitaker
Cris Orfescu
Dena Elisabeth Eber
Doug Craft
Gabriele Peters
Gina Gibson
Gloria DeFilipps Brush
Jason Conti
Jing Zhou
John Antoine Labadie
Lina Marta Sarma
Margie Labadie
Max Morenberg
Michael Wright
Mohammad M. Al-Rifaie
Natalie Wasserman
Philip Sanders
Sarah Epstein
Teja Krasek
WC Corbett
Ying Tan
© Joohyun Jung Pyune ~ Before Me
CGiV2017 Forum
CGiV2017 | The 14th Annual Animation and Digital Effects Film Festival
22 - 25 May 2017 | Cadi Ayyad University | Marrakesh | Morocco |
Technical Directors: Pavel Antipov D.B.M.
Graphics Images: Prof. Dr Marek Zelazo
Producers:
Prof. Mark McK Bannatyne Prof. Jian J. Zhang Theodor Wyeld
Reviewing Jury:
Daniel L. Baldwin L.M. Bannatynov
Anthony C. Cory Jason Guy
Dana Jaksto
Films: Shell Game (Canada)
Adult Hair (France) Wildlife Crossing (Czech Republic)
My Life (Russia) Czarny Punkt (Poland)
El Vendedor De Humo (Spain)
Blow me a Kiss (India) The Butterfly Effect ( United Kingdom)
Egg Change (United States) Sponsor:
Purdue University, USA Bounemouth University, UK
Fliner University, Australia
CGiV2017 _ Doctoral Research Workshop
CGiV2017 Forum
9 t h D o c t o r a l R e s e a r c h W o r k s h o p
Organised by Computer Graphics, Imaging and Visualization Conference
In cooperation with
&
The Computer Graphics, Imaging and Visualization Conference (CGiV) is an international conference that aims to provide a
foundation for integrating the Computer Graphics, Imaging and Visualisation to promote international exchange, cooperation and development. Building upon the reported success of last year’s workshop, CGiV is pleased to announce the “9th Doctoral Research Workshop” which will run as part of the 14th International Conference on Computer Graphics, Imaging
and Visualization (CGiV2017).
Doctoral Research workshop This workshop focuses on the issues that doctoral students face during their studies and includes following interactive sessions – the theme for this year is Research Impact for (PhD) researcher.
The workshop will be hands-on with short inputs from the instructor and time to work on the exercises and own projects
where the instructor and researchers will operate as sparring partner in a friendly environment.
CGiV2017 _PROGRAMME
1 | CGiV2017
Monday 22 May 2017
09:00 < Cadi Ayyad University | Marrakesh ● Faculty of Sciences Semlalia ● Conference room 1>
Registration 9:30 < Cadi Ayyad University | Marrakesh ● Faculty of Sciences Semlalia ● Conference room: Amphitheatre 10>
Opening & Welcome Conference Chair:
Dean of faculty of Sciences Semlalia, Cadi Ayyad University, Marrakesh, Morocco
Prof. A. ZEROUAL, FSSM, Cadi Ayyad University, Morocco
Prof. Mohamed Fakir, Faculty of Sciences and Technics, Sultan Moulay Sliman University, Morocco
Prof. Muhammad Sarfraz, Department of Information Science, Kuwait University, Kuwait
Prof. Ebad Banissi, London South Bank University, UK
Session CGiV2017_1.1: Visualisation Chair: Prof. Ebad Banissi, London South Bank University, UK
<keynote Lecture> NanoSat the future of Space & Application
Dr. Mohamed Kayyali, Founder of KSF Space Foundation, UK
<keynote Lecture> Visualizing Big Hierarchical Data with CabinetTree
Prof. Kang Zhang, Computer Science, The University of Texas at Dallas, USA
11:00 Morning Coffee Break / Photograph Session
CGiV2017 _PROGRAMME
2 | CGiV2017
12:00 < Cadi Ayyad University | Marrakesh ● Faculty of Sciences Semlalia ● Conference room: 2 >
Session CGiV2017_1.2: CGiV _Application Chair: Prof. Kang Zhang, Computer Science, The University of Texas at Dallas, USA
Dimensionality Reduction with Unsupervised Ensemble Learning using K-means Variants
Ameni Filali
New Method of Classification to detect Alzheimer Disease
Amira Ben Rabeh, Faouzi Benzarti, Hamid Amiri
Rendering Style and Viewer’s Perception of Historic Virtual Architecture
Wei Tang, Nicoletta Adamo-Villani
13:00 Lunch Break
14:30 -
15:30
< Cadi Ayyad University | Marrakesh ● Faculty of Sciences Semlalia ● Conference room: 2 >
Session cgiv2017_1.3: CGiV-Application Chair: Prof. M. Fakir, Sultan Moulay Sliman University, Morocco GEODESIC DISTANCE ON RIEMANNIAN MANIFOLD USING JACOBI ITERATIONS IN 3D FACE RECOGNITION SYSTEM AHDID Rachid, SAFI Said, FAKIR Mohamed, MANAUT Bouzid
SURF-DAISY feature detector-descriptor combination for 2D laparoscopic image registration
Wiem Takrouni, Taher khadraoui, Faouzi benzarti
A Rational Quadratic Trigonometric Spline with Interval Shape Control
Muhammad Sarfraz
15:30 Coffee Break
CGiV2017 _PROGRAMME
3 | CGiV2017
15:50 -
16:30
< Cadi Ayyad University | Marrakesh ● Faculty of Sciences Semlalia ● Conference room: 2 >
Session cgiv2016_1.4: Medical Imaging
Chair: Prof. A. ZEROUAL, FSSM, Cadi Ayyad University, Marrakesh Morocco
Automatic Breast Pectoral Muscle Segmentation on Digital Mammograms using Morphological Watersheds TAIFI Khaddouj, AHDID Rachid, FAKIR Mohamed, SAFI Said, ELBALAOUI Abderrahmane, TAIFI Naima
Segmentation of optic disc in fundus images Abderrahmane Elbalaoui, Mohamed Fakir, Youssef OUADID, Khaddouj Taifi, Abdelkrim Merbouha
16:30 -
17:00
< Cadi Ayyad University | Marrakesh ● Faculty of Sciences Semlalia ● Conference room: 2 >
Session cgiv2017_1.5: Animation, Special Effects and Multimedia Show
Chair: Prof. Mark McK Bannatyne, Purdue University, IUPUI Campus, USA
17:00 -
18:00
< Cadi Ayyad University | Marrakesh ● Faculty of Sciences Semlalia ● Conference room: 2 >
Chair: Ebad Banissi, London South Bank University, UK
CGiV2017_ Special Interest Group: Collaborative Research Meeting
CGiV2017 _PROGRAMME
4 | CGiV2017
Tuesday 23 March 2017 09:00 < Cadi Ayyad University | Marrakesh ● Faculty of Sciences Semlalia ● Conference room 1>
Registration 09:30
- 11:00
< Cadi Ayyad University | Marrakesh ● Faculty of Sciences Semlalia ● Conference room: 2 >
Session cgiv2017_2.1: CGiV Application
Chair: Prof. Ebad Banissi, LSBU, UK
Review of Computer Assisted Diagnosis to Analyze the MRI (Magnetic Resource Image) and Detect Alzheimer Disease
Amira Ben Rabeh, Faouzi ben rabeh, Hamid Amiri
Stem & Leaf Plots Extended to Various Ranges of Text Richard Brath, Ebad Banissi
Tumor Detection in Mammography Images Using Fuzzy C-means and GLCM Texture Features
Moustapha Mohamed Saleck, Abdelmajide El Moutaouakkil, Mohammed Mouçouf
CUBIC TRIGONOMETRIC BEZIER SPIRAL CURVES
MD YUSHALIFY MISRO, AHMAD RAMLI, JAMALUDDIN MD ALI, NUR NADIAH ABD HAMID
Thermal image analysis for detection of Pipes and Steel bars in a Concrete Wall
Sougrati Belattar
11:00 Afternoon Coffee Break 11:45 < Cadi Ayyad University | Marrakesh ● Faculty of Sciences Semlalia ● Conference room: 2 >>
Session cgiv2016_2.2: CGiV Application
Chair: Dr. Taher khadhraoui, ENIT, Tunisia
Handwritten Tifinagh Character Recognition through a Structural Approach
Youssef OUADID, Brahim MINAOUI, Abderrahmane ELBALAOUI, Mohamed FAKIR
<keynote Lecture> The Future of Text Visualization
Richard Brath, Uncharted Software, Canada
13:00 Lunch Break
CGiV2017 _PROGRAMME
5 | CGiV2017
14:00
-
17:00
< Cadi Ayyad University | Marrakesh ● Faculty of Sciences Semlalia ● Conference room 2 >
Session cgiv2016_2.3: Doctoral Research Workshop
Chairs: Prof. Ebad Banissi, London South Bank University, UK
14.00 Research Impact
15:00 Student Project Discussion
15:30 Break
16:00 Student Project Discussion
16:45 Group Discussion
17:00 Close
CGiV2017 _PROGRAMME
6 | CGiV2017
Wednesday 24 May 2017
09:00 < Cadi Ayyad University | Marrakesh ● Faculty of Sciences Semlalia ● Conference room 1>
Registration 09:30
– 11:15
< Cadi Ayyad University | Marrakesh ● Faculty of Sciences Semlalia ● Conference room: 2 >
Session cgiv2017_3.1: Visualisation
Chair: Prof Sougrati Belattar, FSSM, Cadi Ayyad University, Marrakesh Morocco PYTHAGOREAN HODOGRAPH QUINTIC TRIGONOMETRIC BEZIER TRANSITION CURVE
MD YUSHALIFY MISRO, AHMAD RAMLI, JAMALUDDIN MD ALI, NUR NADIAH ABD HAMID
Digital Images Securisation by Artificial Neural Networks
TARIK HAJJI, MOHAMMED OUAZZANI JAMIL, El MILOUD JAARA
AUTOMATIC FACE RECOGNITION SYSTEM USING ISO-GEODESIC CURVES IN RIEMANIAN MANIFOLD
AHDID Rachid, TAIFI Khaddouj, SAFI Said, FAKIR Mohamed, MANAUT Bouzid
Approach for tracking human being in survaillance videos
Wafae Mrabti, Driss Moujahid, Kaoutar Baibai, Benaissa Bellach, Hamid Tairi
Diacritic Arabic Character Ontology
Houda Nakkach, Hamid Amiri 11:15 Morning Coffee Break 11:45
- 13:00
< Cadi Ayyad University | Marrakesh ● Faculty of Sciences Semlalia ● Conference room: 2 >
Session cgiv2017_3.2: Image & Video Analysis
Chair: Prof. TARIK HAJJI, Faculté des Sciences de l’Ingénieur, Université Privée de Fès, Morocco
Visual Scene Prediction for Blind People Based on Object Recognition Hanen Jabnoun, Faouzi Benzarti, Hamid Amiri
Blind Radio Mobile Channel Estimation and Identification
Said ELKASSIMI
A Novel Selective Encryption DWT-based Algorithm for Medical Images
Med Karim Abdmouleh, Ali Khalfallah, Med Salim Bouhlel
CGiV2017 _PROGRAMME
7 | CGiV2017
13:00
Lunch Break 14:00 cgiv2017-Committee Members Meeting 14:30
- 17:30
Social & Cultural Networking Event
cgiv2017_Social & Cultural Networking Event Wednesday 24 May 2017– Social & Cultural Networking Event:
This tour has been organised for the conference delegates. Detail of this tour is as follows: Scheduled: Wednesday 24 May 2017 Time: 3 hours Starting: 14:30
Type of Function: Visit of old Medina
20:00 -
22:30
cgiv2017 _ Social Networking Event
Social Networking Event Conference Dinner <further details shortly>
CGiV2017 _PROGRAMME
8 | CGiV2017
Thursday 25 May 2017 9:30 < Cadi Ayyad University | Marrakesh ● Faculty of Sciences Semlalia ● Conference room: 2 >
Session cgiv2017_4.1: CGiV_Application
Chair: Dr Saida IBNYAICH, FSSM, Cadi Ayyad University, Marrakesh Morocco
Designing for Game-based Learning Model: The Effective Integration of Flow Experience and Game Elements to Support Learning
Hussein Karam Abd El-Sattar
An Efficient Compression Scheme for Medical Images Using Hybrid Coders
Sid Ahmed EL Hannachi, Nacréra Benamrane
Does Character's Visual Style affect Audience Empathy and Sympathy?
Jisu Park, Nicoletta Adamo-Villani, Raymond Hassan
Nondestructive Testing Evaluation of Aircraft Fuselage Corrosion by Infrared Thermography and Finite Element Method
Abderrahman Eddazi, Sougrati Belattar
Motorcycle Detection using Support Vector Machine and HOG Features
Pitchaya Jamjan, Waris Rattananimit
11:00 Morning Coffee Break
CGiV2017 _PROGRAMME
9 | CGiV2017
11:30 - 12:30 *
< Cadi Ayyad University | Marrakesh ● Faculty of Sciences Semlalia ● Conference room: 2 > Session cgiv2017_4.2: CGiV - Visualisation
Chair: Prof. Ebad Banissi, LSBU, UK
Robust Video Co-Segmentation Based on Co-saliency of Superpixels
Guoheng Huang, Chi Man PUN
Gabor-Features based Local Generic Representation for Face Recognition with Single Sample per Person
Taher khadhraoui, Sami Ktata, Minyar Sassi Hidri
Conference Closing & Best Paper Awards from cgiv2017 committee: Co-Chairman:
Prof. A. ZEROUAL, FSSM, Cadi Ayyad University, Morocco
Prof. M. Fakir, Faculty of Sciences and Technics, Sultan Moulay Sliman University, Morocco
Prof. Ebad Banissi, BDIRG, LSBU, UK
Prof. Muhammad Sarfraz, Department of Information Science, Kuwait University, Kuwait 12:30 Lunch Break Close
CGiV2017 _Abstract
10 | CGiV2017
ABSTRACTS
Session CGiV2017_1.1: Visualisation Chair: Prof. Ebad Banissi, London South Bank University, UK
<keynote Lecture> NanoSat the future of Space & Application
Dr. Mohamed Kayyali, Founder of KSF Space Foundation, UK
Whatever the next generation of space technology towards R&D, industry and commercial applications is, NanoSat would be the leading era for the upcoming decade, over 400NanoSat launched every single year and over 3500 NanoSat will be launched up to 2020, definitely this would reflect the importance of NanoSat era among slot of applications like mining, telecom, mapping, bigdata, tracking, military and much more. What are the most future industries and how they will count on NanoSat and for what sort of applications? What is the next education and vocation strategy to adopt such technology for future career builders and employers?
Bio-sketch Dr. Kayyali, Innovation Management from Harvard University at the HBS, a PhD &M.Sc (WCU), he is IEEE Industrial Officer ,and BCS (British Computer Society) Computer Chartered Scientist & Chartered Fellow by the Royal Science Council of United Kingdome & Awarded ELITE by BCS in U.K., his biography listed in Who’s Who in Science and Engineering and he has patent theory, he has many published conferences & journals papers and indexed book at the Library of Congress in U.S.A.-, invited
as key note speaker by U.N. & European Union’s industry foundations International Conferences, he was a researcher visitor at the University of California- Santa Barbara UCSB, he was CEO at Trust Holding Dubai, held Business Advisor at CMCE Dubai, also he has numbers of business technology management consulting works in Latin America, North Africa, Asia and Middle East, he is vice
president of Kuwait & Maroc console Chamber of Commerce & Industry at the CGEM. Currently he is CEO / co-founder of 4D Business Consulting 4dbc.net - a Business Consulting firm founded (a business advisory firm short listed by European Bank of Reconstruction & Developing ebrd.com), founder of ANAhost an ISP company in the U.S.A , founder of Time Business News, President of International Federation of Green ICT and founder of KSF Space a U.K International Space Foundation. He is specialized in: ICT Program Directing & Management, Technology Business Management Consulting, Business Innovation & Entrepreneurship, ICT Business Transformation & Integration, Governance and Portfolio Management, Enterprise-wide Change Management, Architecture and Infrastructure Planning, Green ICTand Space Technology & Space Industry
<keynote Lecture> Visualizing Big Hierarchical Data with CabinetTree
Prof. Kang Zhang, Computer Science, The University of Texas at Dallas, USA
Abstract Hierarchical data could essentially be represented as a tree structure and be visualized as a tree. The traditional Treemaps are the most popular
among many tree visualization approaches. Most tree visualization approaches, however, have been focused on layout algorithms and paid little attention to other display properties and interactions. Furthermore, the structural information in conventional Treemaps is too implicit for viewers to
perceive. This talk will present our recent work on Cabinet Tree, an approach for visualizing big hierarchical data (recently published in Journal of Big Data at http://www.journalofbigdata.com/content/pdf/s40537-015-0022-3.pdf). Cabinet Tree draws branches explicitly to show relational structures, uses a space-optimized layout to maximize space utilization, and adopts coloring and labeling strategies to clearly reveal patterns and
contrast different attributes intuitively. Our quantitative evaluations demonstrate that Cabinet Tree achieves good scalability for increased resolutions and big datasets. A usability evaluation in comparison with other approaches also confirms the effectiveness of Cabinet Tree in visualizing hierarchical overview and user exploration.
CGiV2017 _Abstract
11 | CGiV2017
Bio-sketch Kang Zhang is Professor and Director of Visual Computing Lab, Department of Computer Science, and Professor of Arts and Technology, at the University of Texas at Dallas, and an Adjunct Professor at Tianjin University, China. He received his B.Eng. in Computer Engineering from University of Electronic Science and Technology of China in 1982, Ph.D. from the University of Brighton, UK, in 1990, and Executive MBA from the University of Texas at Dallas in 2011. Prior to joining UT-Dallas, he held academic positions in the UK, Australia,
and China. Dr.Zhang's current research interests include generative art, visual languages, aesthetic computing, managerial aesthetics, and software engineering; and has published over 200 papers in these areas. He has authored and edited six books. Dr Zhang is on the Editorial Boards of Journal of Big Data, The Visual Computer, Journal of Visual Languages and Computing, International Journal of Software Engineering and Knowledge Engineering, and International Journal of Advanced Intelligence."
Session CGiV2017_1.2: Imaging Application Chair: Prof. Kang Zhang, Computer Science, The University of
Texas at Dallas, USA
Dimensionality Reduction with Unsupervised Ensemble Learning using K-means Variants
Ameni Filali
Feature selection aims to diminish dimensionality for construct comprehensible learning models with good generalization performance. Feature selection methods are mostly studied independently according to the type of learning: supervised or unsupervised.
This paper describes a novel feature selection algorithm for unsupervised clustering, that combines two clustering ensembles methods such as
bagging and random subspace method using K-means variants to unlabeled data that estimates the out-of-bag feature importance from an ensemble of partitions. Every partition is constructed using a various bootstrap sample and a random subset of the features. The principal idea of the proposed unsupervised feature selection method is to search for a subset of all features such that the clustering algorithm trained on this feature subset can reach the most identical clustering solution to the one acquired by a set learning method. Experiments are performed on different known data sets for validating our proposed method. The results are promising and competitive with various representative algorithms.
New Method of Classification to detect Alzheimer Disease
Amira Ben Rabeh, Faouzi Benzarti, Hamid Amiri
This paper presents a new method of classification to detect Alzheimer Disease in any step: Early controls, Mild Cognitive Impairment (MCI) and Alzheimer Disease (AD). In this paper, we will present our method of classification, which is based on the results of the method of segmentation Level Set. The success of such a classification method is due to the segmentation method and the extraction of the area to be studied. Also, the descriptors used when extracting the form in order to give us better classification results. We will present our supervised classification method. The method consists in taking into account the 4 learning samples whose entry is closest to the new entry X, according to four distances: Euclidean, Manhattan, Hausdorff, AMED (Average Minimum Euclidean Distance). Base to estimate the output associated with a new input X. We tested our CAD with 75 subjects: 25 Normal (age±SD=60±8 years), 25 MCI (age±SD=65±8 years) and 25 Alzheimer (age±SD=60±8 years). The method proved an accuracy of 92% at Alzheimer Disease detection. Our method can be a useful tool to diagnose Alzheimer Diseases in any Step.
CGiV2017 _Abstract
12 | CGiV2017
Rendering Style and Viewer’s Perception of Historic Virtual Architecture
Wei Tang, Nicoletta Adamo-Villani
The paper presents a study that investigated the effect of rendering style on users’ perception of 3D historic architectural environments. Three architectural styles were considered (Traditional Chinese, Gothic and Classic Greek) and three rendering approaches (photorealistic, non-photorealistic – watercolor, and non-photorealistic – technical illustration) were used to render two landmark buildings for each architectural style. 150 subjects were asked to rate the rendering results according to different aspects of perception. Findings show that photorealistic rendering was rated highest for visual appeal and clarity and accuracy of representation of the architectural style, design elements and architectural details; recognition of the architectural style was highest for the non-photorealistic - watercolor renderings.
Session cgiv2017_1.3: CGiV-Application Chair: Prof. M. Fakir, Sultan Moulay Sliman University, Morocco GEODESIC DISTANCE ON RIEMANNIAN MANIFOLD USING JACOBI ITERATIONS IN 3D FACE RECOGNITION SYSTEM AHDID Rachid, SAFI Said, FAKIR Mohamed, MANAUT Bouzid
In this paper, we present an automatic application of 3D face recognition system using geodesic distance in Riemannian geometry. We consider, in this approach, the three-dimensional face images as residing in Riemannian manifold and we compute the geodesic distance using the Jacobi iterations as a solution of the Eikonal equation. The problem of solving the Eikonal equation, unstructured simplified meshes of 3D face surface, such as tetrahedral and triangles are important for accurately modeling material interfaces and curved domains, which are approximations to curved surfaces in R3. In the classifying step, we use: Neural Networks (NN), K-Nearest Neighbor (KNN) and Support Vector Machines (SVM). To test this method and evaluate its performance, a
simulation series of experiments were performed on 3D Shape REtrieval Contest 2008 database (SHREC2008).
SURF-DAISY feature detector-descriptor combination for 2D laparoscopic image registration
Wiem Takrouni, Taher khadraoui, Faouzi benzarti
Image registration is a crucial requirement in many robotic-assisted minimally-invasive surgery (MIS) applications such as Augmented-Reality (AR), shape recovery, structure from motion, and stereo reconstruction. Whereas geometric-based registration is strongly sensitive to the choice of 2D keypoint detector and descriptor, the combination of different detector and descriptor has become an active research area. Despite its effectiveness, there are a few attentions in the last decades. Consequently, keypoints are usually detected and described by applying the Scale Invariant Feature Transform (SIFT) or Speeded-Up Robust Features (SURF). Herein, we introduce a new descriptor in order to describe the laparoscopic image keypoints combining with SURF detector. The objective behind this combination is to change the SURF detector to be invariant to rotation and deformation. The registration is then performed using the Iterative Closest Point K-means (ICPK-means) which increase the speed and improve the accuracy. Realized experiments on 100 nephrectomy laparoscopic frames demonstrated the effectiveness of the proposed method for laparoscopic image registration and showed its superiority over state-of-the-art methods.
A Rational Quadratic Trigonometric Spline with Interval Shape Control
Muhammad Sarfraz
An interpolation curve scheme is constructed to design planar objects using a rational quadratic trigonometric spline with interval shape control (RQTSISC). The spline curve, achieved through the constructed scheme, possesses the best possible geometric properties such as convex hull, partition of unity, affine invariance and variation diminishing and some important shape properties such as local and global interval shape
CGiV2017 _Abstract
13 | CGiV2017
(tension) properties which provide good control on the curve and help in modifying the shape as one can desire. Moreover proposed method performance has smoothness of degree 2.
Session cgiv2016_1.4: Medical Imaging
Chair: Prof. A. ZEROUAL, FSSM, Cadi Ayyad University,
Marrakesh Morocco
Automatic Breast Pectoral Muscle Segmentation on Digital Mammograms using Morphological Watersheds TAIFI Khaddouj, AHDID Rachid, FAKIR Mohamed, SAFI Said, ELBALAOUI Abderrahmane, TAIFI Naima
The segmentation of mammograms plays a major role in isolating areas which can be subject of tumor. The identification of these zones is generally done in three steps: pectoral muscle segmentation, hard density zone detection and texture analysis of regions of interest. This paper deals with the segmentation of the pectoral muscle on a mammography image, in order to facilitate the work of experts while analyzing. The developed methodology is based on Morphological Watersheds. This algorithm has been tested on 80 digital mammography images of MIAS database. The performance is evaluated based upon the false positive (FP), false negative (FN) pixel percentage, and mean distance. All the average FN and FP pixel percentages are 3.68% and 2.98%, with the range shown from 0.90 to 0.99 for accuracy and 0.86 to 0.99 for precision rate. The method is also compared with three well-known pectoral muscle detection techniques and in most of the cases; it outperforms the other three approaches.
Segmentation of optic disc in fundus images Abderrahmane Elbalaoui, Mohamed Fakir, Youssef OUADID, Khaddouj Taifi, Abdelkrim Merbouha
A successful optic disc (OD) segmentation is an important task for automated detection white lesions related to diabetic retinopathy. Therefore, exudates detection is our major purpose, but we must extract the OD prior to the process because it appears with similar color, intensity and contrast to other characteristics of the retinal image. The retinal image consists of blood vessels that emerge from the OD. The presence of these blood vessels may act as a disturbance for the detection of OD. This paper presents a novel method for segmentation of the OD in retinal images. The methodology includes localization of OD center, followed by elimination of vascular structure using inpainting method. Finally, an active contour model was applied to boundary OD segmentation with a variational level set formulation. The results are compared with a ground truth image from the ophthalmologist. The source retinal image for performing this work is obtained from the publicly available DRIVE and MESSIDOR database. This method offers a successful segmentation of OD which may help in diagnosis of various retinal abnormalities.
CGiV2017 _Abstract
14 | CGiV2017
Session cgiv2017_2.1: Medical Imaging
Chair: Prof. Ebad Banissi, LSBU, UK
Review of Computer Assisted Diagnosis to Analyze the MRI (Magnetic Resource Image) and Detect Alzheimer Disease
Amira Ben Rabeh, Faouzi ben rabeh, Hamid Amiri
Technological evolution has led to biomedical data acquisitions increasingly voluminous, heterogeneous and complex require efficient and timely systems to analyze and treatments to help physicians define diagnoses and appropriate prognoses in a timely manner. Support systems for Decision-making based on Biomedical Computing have become ubiquitous in clinical settings. In this context, we present in the first part of this article the main steps and components of a Computer-Assisted Diagnosis CAD system from the MRI (Magnetic Resonance Imaging) data. In the second part, we present some existing CAD systems to detect Alzheimer's disease (AD) at an early stage.
Stem & Leaf Plots Extended to Various Ranges of Text
Richard Brath, Ebad Banissi
Stem and leaf plots are data dense visualizations that organize large amounts of micro-level numeric data to form larger macro-level visual distributions. These plots can be extended with font attributes and different token lengths for new applications such as n-grams analysis, character attributes, set analysis and text repetition.
Tumor Detection in Mammography Images Using Fuzzy C-means and GLCM Texture Features
Moustapha Mohamed Saleck, Abdelmajide El Moutaouakkil, Mohammed Mouçouf
The Fuzzy C-means (FCM) is one of the most efficient algorithms used in various
studies which aims at segmenting the masses in mammogram images, thus to
build a computer aided diagnosis (CAD) system capable of helping the physicians
for an early diagnosis of the breast cancer. In this paper, we will introduce a new
approach using FCM algorithm, in order to extract the mass from region-of-
interested (ROI). The proposed method aims at avoiding problematic of the
estimation of the cluster number in FCM by selecting as input data, the set of
pixels which are able to provide us the information required to perform the mass
segmentation by fixing two clusters only. The Gray Level Occurrence Matrix
(GLCM) is used to extract the texture features for getting the optimal threshold,
which separate between selected set and the other sets of the pixels that influences
on the mass boundary accuracy. The performance of the proposed method is
evaluated by specificity, sensitivity and accuracy. The results obtained from
experimentations shows a good efficiency at the different measures used, in favor
of our method
CUBIC TRIGONOMETRIC BEZIER SPIRAL CURVES
MD YUSHALIFY MISRO, AHMAD RAMLI, JAMALUDDIN MD ALI, NUR NADIAH ABD HAMID
Shape parameters in trigonometric Bezier curves are very useful in providing flexibility to construct the desired curve. It helps users to find the best curve when dealing with designing and modeling tasks. It can simply be used without needing to change control points or using weightage in rational function. A technique for composing five templates of transition curves constructed by cubic trigonometric Bezier spiral is examined and presented.
Thermal image analysis for detection of Pipes and Steel bars in a Concrete Wall
Sougrati Belattar
Infrared thermography became a powerful method of thermal imaging analysis and detection applied in nondestructive testing domain, especially in the civil engineering field.
CGiV2017 _Abstract
15 | CGiV2017
By exciting the structure under test by an external thermal heat flux and analyzing the propagation of heat in the examined region and the obtained thermal image one can, with appropriate treatment, highlight the presence of an internal defect of the considered structure such as cracks, delamination or corrosion.
In this work, a method of thermal image analysis of civil engineering structures, based on the finite element method and the infrared thermography principle for detection of bodies of water pipe or steel bars type in building wall is presented.
Session cgiv2016_2.2: CGiV Application
Chair: Dr. Taher khadhraoui, ENIT, Tunisia
Handwritten Tifinagh Character Recognition through a Structural Approach
Youssef OUADID, Brahim MINAOUI, Abderrahmane ELBALAOUI, Mohamed FAKIR
In this article, we present a handwritten Tifinagh character recognition system based on a structural approach which is graph representation. It is composed of three main steps: pre-processing, features extraction and classification. In the pre-processing step, thresholding, normalization and thinning are applied to enhance the quality of the image. In the feature extraction step, corners are extracted using a proposed algorithm then represented by graph. In the classification step, graphs are compared using a graph matching method. Experimental results are obtained using a recently created database of handwritten Tifinagh characters to test the effectiveness. The system shows good results in terms of accuracy.
<Key note lecture> The Future of Text Visualization
Richard Brath Uncharted Software, Canada Visualization of text has lagged behind the visualization of quantitative data. Text analytics are significantly advancing, but the most famous text visualization is the tag cloud which has many criticisms. One can find inspiration by looking beyond the visualization community: calligraphers, typographers, cartographers, mathematicians, and other fields have long traditions of text supplemented with additional information embedded into formats and layouts. Many of these old techniques can be re-discovered and inform new kinds of text visualizations. These communities can also provide insight into different applications of text and different criteria to evaluate text visualizations. As a result, there is a broad opportunity for innovation in text visualization
Bio-sketch
Richard Brath has been involved in the design and
development of interactive visualization for the last 25 years. These include the first interactive 3D financial visualization on the web (1996) and other early visualizations; to a wide variety of visualizations in use today by hundreds of thousands of users. Together with David Jonker, Richard published Graph Analysis and Visualization with Wiley books (2015). Richard is a partner at Uncharted Software. He had
degrees in both design and software and remains active in visualization research including an in-progress PhD in visualization
CGiV2017 _Abstract
16 | CGiV2017
Session cgiv2016_2.3: Doctoral Research Workshop
Chairs: Banissi, Prof. Ebad, London South Bank University, UK
14.00 Research Impact
15:00 Student Project Discussion:
15:30 Break
16:00 Student Project Discussion:
16:45 Group Discussion
17:00 Close
CGiV2017 _Abstract
17 | CGiV2017
Session cgiv2017_3.1: Visualisation
Chair: Prof Sougrati Belattar, FSSM, Cadi Ayyad University,
Marrakesh Morocco
PYTHAGOREAN HODOGRAPH QUINTIC TRIGONOMETRIC BEZIER TRANSITION CURVE
MD YUSHALIFY MISRO, AHMAD RAMLI, JAMALUDDIN MD ALI, NUR NADIAH ABD HAMID
Pythagorean Hodograph (PH) quintic transition curves are normally constructed because it is polynomial and has attractive properties, which is its arc-length is a polynomial of its parameter, and the formula for its offset is a rational algebraic expression. Pythagorean Hodograph is very important in formulating efficient real-time interpolator algorithm for CNC machines, suitable for rounding corners and blending smooth transition between two circles. By reinstating quintic Bezier curve with quintic trigonometric Bezier curve with two shape parameters, it will provide more flexibility to construct curves and surfaces. This new type of Pythagorean Hodograph will be more practical for curve designing especially in the computer aided geometric design of consumer products and useful for other computer graphics for designing highways.
Digital Images Securisation by Artificial Neural Networks
TARIK HAJJI, MOHAMMED OUAZZANI JAMIL, El MILOUD JAARA
We find in this work a description of a new contribution in watermarking for digital images security. The objective of this paper is design methods to protect the digital image integrity using artificial neural networks (ANN) to digitally signing an image.
AUTOMATIC FACE RECOGNITION SYSTEM USING ISO-GEODESIC CURVES IN RIEMANIAN MANIFOLD
AHDID Rachid, TAIFI Khaddouj, SAFI Said, FAKIR Mohamed, MANAUT Bouzid
In this paper, we present an automatic 3D face recognition system. This system is based on the representation of human faces surfaces as collections of Iso-Geodesic Curves (IGC) and Matrix of Geodesic Distances (MGD) using 3D Fast Marching algorithm. To compare two facial surfaces, we compute a geodesic distance between a pair of facial curves using a Riemannian geometry. In the classifying step, we use: Neural Networks (NN), K-Nearest Neighbor (KNN) and Support Vector Machines (SVM). To test this method and evaluate its performance, a simulation series of experiments were performed on 3D Shape REtrieval Contest 2008 database (SHREC2008).
Approach for tracking human being in survaillance videos
Wafae Mrabti, Driss Moujahid, Kaoutar Baibai, Benaissa Bellach, Hamid Tairi
Tracking the moving human beings in image sequences using a stationary camera is a crucial task for diverse surveillance videos applications. The main objective of this paper is to propose a new approach, which combines the Kalman Filter and the Support Vector Machines for accomplishing this task. First, the moving target is determined according to the user’s interest, and then the system state model of Kalman Filter is constructed. Second, a set of patterns are generated around the target’s position. For every pattern, the Histogram of Oriented Object is calculated to be classified into positive (humans) and negative patterns (other object) by the Support Vector Machines.
Finally, the selected pattern is the one that minimizes the Euclidean distance between the prediction and the positive patterns. This selected pattern is considered as a measurement for the correction step of Kalman Filter. The experiment results prove that the proposed method has the robust ability to track the moving human being across the image
CGiV2017 _Abstract
18 | CGiV2017
sequences with different challenging situations such as occlusion, deformation, rotation, low resolution and the scale variation.
<Short Paper> Diacritic Arabic Character Ontology
Houda Nakkach, Hamid Amiri
The main objective of our work is the online character recognition based on an ontology domain. So, this paper presents the creation of a CHAKEL-Onto ontology based on an expert in the domain. CHAKEL-Onto models the Arabic diacritical characters, presents 7 concepts, 36 spatial relations, 65 Rules of inference, 830 individuals. The CHAKEL-Onto is available for the purpose to improve Ontolgy research filed.
Keywords: CHAKEL-Onto, Arabic Character, Diacritical Marks, Ontology, online Arabic character recognition, spacial relation
Session cgiv2017_3.2: Image & Video Analysis
Chair: Prof. TARIK HAJJI, Faculté des Sciences de l’Ingénieur,
Université Privée de Fès, Morocco
Visual Scene Prediction for Blind People Based on Object Recognition Hanen Jabnoun, Faouzi Benzarti, Hamid Amiri
Vision is one of the very essential human senses and it plays the most important role in human perception about surrounding environment. Hence, over published papers on these subjects that propose a variety of computer vision products and services by developing new methods for scene understanding. This work aims to introduce an approach that restores a central function of the visual system which is the interpretation of visual scene. The proposed method is based on the identification of surrounding objects in dissimilar frames from video scene. The experimental results using feature extractions showed good accuracy for detecting object under different conditions. Object recognition using features extraction and Bag of Visual Words correspondence is exploited for scene type understanding.
Blind Radio Mobile Channel Estimation and Identification
Said ELKASSIMI
This paper resolve the problem radio mobile channel estimation and identification by blind algorithms. For this, we have proposed two algorithms, which are compared with cumulants based algorithms. However, the simulation results in noisy environment and for different SNR values with QPSK or 4QAM modulation show that the proposed algorithms gives a good estimation and identification versus to the cumulants algorithms, for radio mobile channel.
A Novel Selective Encryption DWT-based Algorithm for Medical Images Med Karim Abdmouleh, Ali Khalfallah, Med Salim Bouhlel
The remarkable development of the medical imagery is due to the large use of telecommunications and information technologies in the medical domain. However, since the telemedicine is a medical act that must answer to stern rules, and follow the easiness that is offered by the informatics sciences to violate the confidentiality and authenticity of medical data. To resolve this problem, a lot of methods combining compression and encryption have been developed in the literature to secure the transmission and the storage of medical images. In this paper, we propose a new approach of partial encryption based on the Discrete Wavelet Transform (DWT) and compatible with the norm JPEG2000 in order to assure an optimal and a secure transmission and storage of medical images. This approach is, on one hand, faster since it permits a very important gain in the encryption-decryption processing time (only 6.25% of the DWT matrix coefficients will be encrypted), and on the other hand more efficient because it permits to get an encrypted medical image.
CGiV2017 _Abstract
19 | CGiV2017
Session cgiv2017_4.1: CGiV_Application
Chair: Dr Saida IBNYAICH, FSSM, Cadi Ayyad University,
Marrakesh Morocco
Designing for Game-based Learning Model: The Effective Integration of Flow Experience and Game Elements to Support Learning
Hussein Karam Abd El-Sattar
Game-based learning (GBL) is growing rapidly as a gaming industry as well as a field of academic research. Developing GBL is not an easy task. It requires a tight collaboration with domain experts and this need considering a complex mix of disciplines and technologies. Learning theory, learning contents, and game design are three multidisciplinary challenges involved in proper GBL development. This paper attempts to address these challenges by demonstrating how GBL can be conceptualized from different theoretical perspectives on learning and discuss a number of fundamental elements of game design that are essential for effective learning. Then, we propose a novel methodology of design and development of GBL model that facilitates the integration of flow experience with such game elements to support learning in games. The flow theory is used as a framework to facilitate a positive user experience in order to maximize the impact of GBL. Comparisons with existing frameworks are included. Evaluation and practical performance results supported by some case study called “A day without computer-mediated technology” are also demonstrated to verify the usability of the proposed model.
An Efficient Compression Scheme for Medical Images Using Hybrid Coders
Sid Ahmed EL HANNACHI, Nacréra BENAMRANE
Medical images have to be transmitted across telemedicine network medical centre for diagnosis. In this regard, effective lossy compression algorithms or near lossless algorithms have to be developed, giving high compression ratios to reduce the amount of storage and transmission
required The purpose of this paper is to present a new near lossless medical image compression scheme, based on Integer Wavelet Transform (IWT) and Lattice Vector Quantization (LVQ). An improvement in compression ratio is achieved by applying the good energy compaction of Integer Discrete Cosine Transform (IDCT) on the low frequency subband, while maintaining a visual quality of reconstructed images significantly. Experimental results demonstrate that the proposed coding scheme achieves considerably better performance as compared to other methods.
Does Character's Visual Style affect Audience Empathy and Sympathy?
Jisu Park, Nicoletta Adamo-Villani, Raymond Hassan
A believable virtual character is able to emotionally interact with the audience. To achieve believability, every component of the character from its movement to its appearance should be carefully designed. However, to date, few studies have investigated what visual factors trigger the emotional interaction between character and audience. The purpose of this experimental study was to examine the effect of visual styles of 3D animated characters on audience empathy and sympathy responses. In the study, seventy-one participants watched three animations of three characters whose visual style differed in degree of stylization (e.g. lead, stylized, and iconic). In each animation, the characters showed happy, angry and sad emotions. After viewing each character's animation, participants responded to a survey that measured their empathy and sympathy levels. Findings from the study show that character’s visual style does not seem to have a significant effect on audience empathy and sympathy.
Nondestructive Testing Evaluation of Aircraft Fuselage Corrosion by Infrared Thermography and Finite Element Method
Abderrahman Eddazi, Sougrati Belattar
In this paper, we are studying the nondestructive investigation of transport aircraft fuselage using infrared thermography and finite element method
CGiV2017 _Abstract
20 | CGiV2017
for a quicker and easier inspection. We will focus on the solution of the heat equation to analyze the evolution of the temperature on the external surfaces of the model.
The nondestructive inspection of structures by infrared thermography requires considering some limitations such as dimension, position, thermophysical properties of the defect, temperature, heat flux.
To do an investigation of the corrosion within the aircraft structure to be studied, we chose an aluminium fuselage wherein corrosion, resulted from a chemical reaction, was inserted. The simulation is done by changing heat flux and thickness of corrosion to determine the degree of detectability of the infrared thermography method by analysis of the resulted temperature differences for each heat flux value and for each corrosion thickness.
<Poster Paper>
Motorcycle Detection using Support Vector Machine and HOG Features
Pitchaya Jamjan, Waris Rattananimit
In our proposed system, motorbikes are detected in footpath. Usually footpath is used by people for walking or running and not allowing for Motorcycles. But in Thailand, many Motorcycles are illegally used in footpath in order to avoid traffic jam. This research is aim to develop the system to capture the image and video which are evidences for law enforcement. This method is to base on features of Motorcycles in a video frame. We apply classified using a support vector machine (SVM) classifier on histogram of oriented gradients (HOG) features of motorcycle for classification database. The accuracy of detection is 95%.
Session cgiv2017_4.2: CGiV - Visualisation
Chair: Prof. Ebad Banissi, LSBU, UK
Robust Video Co-Segmentation Based on Co-saliency of Superpixels
Guoheng Huang, Chi Man PUN
In this paper, we propose a video co-segmentation based superpixel co-saliency. Our approach is based on a hypothesis, the common or similar
objects in multiple video clips are salient, and they shares the similar feature. At first, we try to find out the regions in every clip which are salient and share the similar feature by proposing a new superpixel co-saliency scheme. Then, the most salient superpixels are chosen as the initial object marker superpixels. Starting from these superpixels, merge the neighboring and similar regions, and segment out the final object parts. The experimental results demonstrate that the proposed model can efficiently segment the common objects from a group of video clips with generally lower error rate than some existing methods.
Gabor-Features based Local Generic Representation for Face Recognition with Single Sample per Person
Taher khadhraoui, Sami Ktata, Minyar Sassi Hidri
This paper presents an approach called Gabor feature-based Local Generic Representation (G-LGR), which take advantages of the sparse representation properties of face recognition in biometric applications. In this work, the main problem is that if only one training subject per class is available. One of the novelties of our new algorithm is to produce virtual samples of each subject; the new sample generic of a gallery set is used in order to generate the intra-personal variations of different individuals. We compare our approach against different state-of-the-art techniques using the AR face database.
CGiV2017 _ NOTES
COMMITTEE
CGiV2017 14th International Conference
Computer Graphics, Imaging and Visualization 22 - 25 May 2017
Cadi Ayyad University ● Marrakesh ● Morocco ● http://www.graphicslink.co.uk/cgiv2017/
Organising committee
Honorary Chair :
• Abdellatif MIRAOUI (President of Cadi Ayyad University, Marrakesh, Morocco)
• My Hassan HBID (Dean of Faculty of Sciences Semlalia, Marrakesh, Morocco)
General Chair :
Prof. Abelouhab ZEROUAL, FSSM, Cadi Ayyad University, Marrakesh Morocco
General Co-Chairs:
• Prof. Mohamed. Fakir, Sultan Moulay Sliman University, Morocco
• Prof. Ebad Banissi, LSBU, UK
• Prof. Muhamed Sarfraz, Kuwait University, Kuwait
Organizing committee
• Prof Sougrati BELATTAR, FSSM, Cadi Ayyad University, Marrakesh, Morocco
• Prof. Moha Mrabet HASSANI, FSSM, Cadi Ayyad University, Marrakesh, Morocco
• Prof. Saida IBNYAICH, FSSM, Cadi Ayyad University, Marrakesh, Morocco
• Prof. Zakaria BOULGHASOUL, ENSA, Cadi Ayyad University, Marrakesh, Morocco
• Prof Samira CHABAA, ENSA, Ibn Zohr University, Agadir, Morocco
• Prof. Jilali ANTARI, FPT, Ibn Zohr University, Agadir, Morocco
• Prof Issam QAFFOU, FSSM, Cadi Ayyad University, Marrakesh, Morocco
Coordinator:
• Anita DPour (GraphicsLink, UK)
CGiV2017 _ NOTES
NOTES
F.T. Marchese, E. Banissi (Eds.)
Knowledge Visualization Currents
From Text to Art to Culture
▶ Presents the state of the art in visualization research and development
▶ Highlights research developing at key intersections with other disciplines and
its applicability to addressing complex real-world problems
▶ Discusses how visualization researchers are addressing complex issues of
representation in knowledge, art, and culture
Lying at the intersection of education, art, and cultural heritage, visualization is a powerful tool for representing and interpreting complex information. This unique text/reference reviews the evolution of the field of visualization, providing innovative examples of applied knowledge visualization from disciplines as varied as law, business management, the arts and humanities. With coverage of theoretical and practical aspects of visualization from ancient Sumerian tablets through to twenty-first century legal contracts, this work underscores the important role that the process of visualization plays in extracting, organizing, and crystallizing the concepts found in complex data. Topics and features:
• Contains contributions from an international selection of preeminent authorities • Presents a thorough introduction to the discipline of knowledge visualization, its current state of affairs
and possible future developments • Examines how tables have been used for information visualization in historical textual documents • Discusses the application of visualization techniques for knowledge transfer in business relationships, and
for the linguistic exploration and analysis of sensory descriptions • Investigates the use of visualization to understand orchestral music scores, the optical theory behind
Renaissance art, and to assist in the reconstruction of an historic church • Describes immersive 360 degree stereographic visualization, knowledge-embedded embodied
interaction, and a novel methodology for the analysis of architectural forms This interdisciplinary collection of the state of the art in knowledge visualization will be of considerable interest to researchers from a broad spectrum of backgrounds in both industry and academia.
Knowledge Management and Information
Retrieval System
Design a system to build Knowledge Management and Information Retrieval System that is based on document and text analysis. This is centred on the frame-work that use textual attributes for visual analytics purpose. This KMIR system is envisaged the following components:
1. Visualisation on Text
a. Search & Visualisation
b. Skim Formatting of Previews
2. Visualization on Lists
a. Search listing
b. Proportional Encoding
c. Entity Extraction
3. Language Analytics
a. Linguistic Analysis
b. Topic Modelling
c. Characteristic Analysis
d. Sentiment Analysis
Application intended: Skimming System (online and off line) Geo-based Knowledge Map Typography and Cartography
Methodology Development
We're looking for:
Students with skills in Apps development, User experience and learning & education and interface design. Applicants should have a strong ambition to design and build technologies to make people's lives better. Further Information contact: Ebad Banissi │Richard Brath: banisse │ brathr @lsbu.ac.uk
Published by:
BDIRG | BIG DATA & INFORMATICS RESEARCH GROUP
London South Bank University
D I G I T A L A R T G A L L E R Y
o n l i n e e x h i b i t i o n May 2017 ~ July 2018
V I R T U A L G A L L E R Y V E N U E
www.g raph ic s l i nk .c o .uk /DART.h tm
© " Inferno Alighieri - in Memoriam " - Cris Orfescu-
©
G
abri
ele
Pet
ers
~D
ark
Day
s N
ew Y
ork
2"
"Inner Shrine": Inspired by the poem "Journey Home" composedby the noted Indian poet, Rabindranath Tagore, combined with my writing, "Inner Shrine" reveals the emotional and spiritual journey in searching of one's soul. To find the inward space of one's own- the home of the heart, one has to experience life to the fullest. It is the most intricate encounter that wanderers have to undertake, through which they discover the essence of their existence and the answer for who we
are. © Jing Ziou