Abstract
Iris recognition is considered as one of the most promising noninvasive biometric systems providing automated human identification. Numerous programs, like unique ID program in India - Aadhar, include iris biometric to provide distinctive identity identification to citizens. The active area is usually captured under non ideal imaging conditions. It usually suffers from poor brightness, low contrast, blur due to camera or subject's relative movement and eyelid eyelash occlusions. Besides the technical challenges, iris recognition started facing sophisticated threats like spoof attacks. Therefore it is vital that the integrity of such large scale iris deployments must be preserved. This paper presents the development of a new spoof resistant approach which exploits the statistical dependencies of both general eye and localized iris regions in textural domain using spatial gray level dependence matrix (SGLDM), gray level run length matrix (GLRLM) and contourlets in transform domain. We did experiments on publicly available fake and lens iris image databases. Correct classification rate obtained with ATVS-FIr iris database is 100% while it is 95.63% and 88.83% with IITD spoof iris databases respectively.
Highlights
Iris recognition is an extensively used biometric system by private and government agencies for its precision and trustworthiness
Iris recognition is an indispensable module of large scale biometric identification for financial transactions and social benefits, e.g. iris biometrics is used in the Aadhar project to provide dependable identification for millions of citizens in India [2]
Author in [3] stated that commercial systems can be fooled with a printout down to a resolution of 1200 dpi, an iris diameter of 75 pixels and at least 75% of the iris being visible. Latest attacks such as those detailed in [4] show more sophisticated threats rising from the usage of textured superficial lenses that present changed iris texture to the iris acquisition system which can possibly compromise the installed iris recognition systems
Summary
Iris recognition is an extensively used biometric system by private and government agencies for its precision and trustworthiness. The developed approach works on spoofed images with printed attacks, while sustaining recognition capability in the presence of soft (transparent) lens. Authors in [10] proved that focus, motion, occlusion and other quality related measures can help fake iris detection The effect of both transparent and colored contact lenses on iris recognition was presented in [4, 5, 7]. Authors in [15] applied Gaussian smoothed as well as SIFT weighted LBP for the detection of textured lens in iris images. The method proposed here works well on print spoof iris images and iris with contact lens using textural and contourlet features
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Engineering, Technology & Applied Science Research
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
