A New Approach Towards Biometric Authentication System Using Face Vein

BATCH MEMBERS

L.NIVETHITHA(111911104066) S.SHOWMIYA(111911104092)

M.SNEHA(111911104094)S.S.SWATHI(111911104104)

GUIDED BY

Mr.H.ANWAR BASHA,M.Tech., (ASSISTANT PROFESSOR)

S.A.Engineering College

OBJECTIVE• This project is concerned with the task of identifying the

individual’s thermal facial signature for the purpose of authentication.

• It includes image acquisition, coding the matching algorithm for processing the face vein pattern and testing of algorithm module. It can also be used to decrease the percentage of false rate and rejection rate identification of a person.

ABSTRACT

A new approach towards biometric authentication system using face vein is to identify the problem of human face recognition. Different approaches to the problems of face detection and face recognition were evaluated and implemented using the Matlab technical computing language. In the implemented frontal-view face detection systems, automated face detection was achieved based on image invariants. The proposed algorithm is fully integrated and consolidates the critical steps of feature extraction through the use of morphological operators, registration using the Linear Image Registration Tool, and matching through unique similarity measures designed for this task. The novel approach at developing a thermal signature template using four images taken at various instants of time ensured that unforeseen changes in the vasculature over time did not affect the biometric matching processes the authentication process relied only on consistent thermal features. The results are based on applying the directional filter with anisotropic diffusion filter and achieved an average accuracy of 87.16% for skeletonized signatures and 94.63% for anisotropically diffused signatures with directional filters. The highly accurate results obtained in the matching process clearly demonstrate the ability of the thermal infrared system to extend in application to other thermal-imaging-based systems.

..\project\Thermal Imaging as a Biometrics Approach to Facial signature authentication.pdf

EXISTING SYSTEM

Identification systems rely on 3 key elements1. Attribute identifiers2. Biographical identifiers3. Biometric identifiersDISADVANTAGES:• It is easy to forge by intruders.• Less secure• Sensitive to light variability and other factors like difficulty in

detecting facial disguises.

PROPOSED SYSTEM

• We are implementing an biometric authentication system which uses facial signature to recognize an person’s identity.

• In this the thermal image are taken and features are extracted.• The extracted features are enhanced by combining diffused

and directional filters.ADVANTAGES: With the combined use of Directional and Diffusional

filter, the images extracted are clear and efficient.

LITERATURE SURVEYS.No Title Author Name of the Jounal Year of Publication Concept Disadvantages

1 Discriminating Color Faces for Recognition 

Jian Yang, Chengjun Liu and Jingyu Yang

International Journal of Recent Technology and Engineering (IJRTE)

dec 2008 •Original image is converted into an RGB image•RGB image is again converted into an gray scale •The gray scale image is enhanced

•Accurate gray scale image

2 Human Biometrics:Moving Towards Thermal Imaging

Nermin K. Negied International Journal of Recent Technology and Engineering (IJRTE) ISSN: 2277-3878, Volume-2, Issue-6, January 2014

Jan 2014 •Uses the heat given of by an object to produce an image•device collects the infrared radiation from the object in the screen and creates an electronic image based on the information

•Image is not clearly visible

3 A NOVEL APPROACH TO FACE RECOGNITION BASED ON THERMAL IMAGING

MG Sanjith Kumar, D Saravanan

IJRET: International Journal of Research in Engineering and Technology Mar-2014

March 2014 •Images captured using Thermal mid wave infrared (MWIR) used to overcome problem of light variations. •Images are captured as electronic spectrum of waves

•The noise in the electronic spectrum waves are to be filtered before registration.

SYSTEM ARCHITECTURE DIAGRAM

DESIGN OF PROPOSED WORK

• Module-I:Thermal infrared-Image Registration& Face Segmentation

• Module-II :Thermal Signature Extraction• Module-III : Feature Matching

MODULES

MODULE-I:Thermal infrared-Image Registration& Face Segmentation• Data is collected using mobile camera system which

operates in thermal vision.• The frontal view of the image is registered.• Using the dual-front contour region growing technique

the face image are segmented from the neck and hair region.

MODULE-II

Thermal Signature Extraction• Noise Removal: The significance of the anisotropic diffusion filter is to

reduce spurious and speckle noise effects seen in the images.

• Image Morphology: The top-hat segmentation is used to enhance the

brightness of the object in the image.• Post Processing: The skeletonization process is used o reduce the

foreground regions into a skeletal remnant that largely preserves the extent and connectivity of the original region.

MODULE-III: Feature Matching: • The thermal signature which is extracted is matched with

the N number of templates stored in the database• If both the template and the signature is matched, the

individual is authorized else they are unauthorized person

USECASE DIAGRAM

SEQUENCE DIAGRAM

CLASS DIAGRAM

ACTIVITY DIAGRAM

COLLABORATION DIAGRAM

DATA FLOW DIAGRAMS

LEVEL 0

LEVEL 1

LEVEL 2

LEVEL 3

LEVEL 4

SCREEN SHOTS

ADVANTAGES

• Passport and visa verification can also be done using face Recognition technology as explained above. Even Driving license verification can also be exercised face recognition technology as mentioned earlier.

• To identify and verify terrorists at airports, railway stations and malls the face recognition technology will be the best choice in India as compared with other biometric technologies since other technologies cannot be helpful in crowd places.

FUTURE ENHANCEMENT

• Next generation person recognition systems will need to recognize people in real-time and in much less constrained situations.

• We believe that identification systems that are robust in natural environments, in the presence of noise and illumination changes, cannot rely on a single modality

REFERENCE

• C. L. Lin and K. C. Fan, “Biometric verification using thermal images of palm-dorsa vein patterns,” IEEE Trans. Circuits Syst. Video Technol.,vol. 14, no. 2, pp. 199–213, Feb. 2004.

• I. Pavlidis, P. Tsiamyrtzis, P. Buddhraju, and C. Manohar, “Biometrics:Face recognition in thermal infrared,” in Biomedical Engineering Handbook,J. Bronzino, Ed. Boca Raton, FL: CRC Press, 2006.

• S. Lankton and A. Tannenbaum, “Localizing region-based active contours,”IEEE Trans. Image Process, vol. 17, no. 11, pp. 2029–2039, Nov.2008.

THANK YOU