Abstract
In this study, we maneuvered a dual-band spectral imaging system to capture an iridal image from a cosmetic-contact-lens-wearing subject. By using the independent component analysis to separate individual spectral primitives, we successfully distinguished the natural iris texture from the cosmetic contact lens (CCL) pattern, and restored the genuine iris patterns from the CCL-polluted image. Based on a database containing 200 test image pairs from 20 CCL-wearing subjects as the proof of concept, the recognition accuracy (False Rejection Rate: FRR) was improved from FRR = 10.52% to FRR = 0.57% with the proposed ICA anti-spoofing scheme.
Highlights
Iris recognition has drawn much attention because of its well-established framework, extremely high accuracy, and computational efficiency [1,2,3]
This study provided a robust algorithm for automatically detecting contact lens (CCL) in iris images
The results indicated that our system was as accurate and robust as those presented in the Iris Challenge Evaluation (ICE) 2006, an iris recognition grand challenge that employed a data set comprising 29,056 right iris and 30,502 left iris images; the three highest-performing systems in the ICE 2006 had false rejection rate (FRR) ranges of roughly 1–2.5% when the false acceptance rate (FAR) was set to 0.1%, according to [48]
Summary
Iris recognition has drawn much attention because of its well-established framework, extremely high accuracy, and computational efficiency [1,2,3]. It is becoming even more popular and has started to be deployed for national-scale applications [4,5]. Many efforts have been made to develop anti-spoofing techniques for iris recognition. Currently there is no anti-spoofing technique which claims to be able to perform iris recognition directly on the CCL-wearing subjects. We have attempted to develop a hardware-software hybrid iris recognition system which deals with CCL-based spoofing. Based on the assumption that the iris texture and CCL pattern are statistically independent in the spectral domain, the proposed system, which combines a dual-band camera (DBC) system with a source separation technique (Independent Component Analysis, ICA), has the capability of separating the spectral component of the natural iris region from the CCLs’
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: 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.
