Abstract
This work addresses the increasing demand for a sensitive and user-friendly iris based authentication system. We aim at reducing False Rejection Rate (FRR). The primary source of high FRR is the presence of degradation factors in iris texture. To reduce FRR, we propose a feature extractionmethod robust against such adverse factors. Founded on local and global variations of the texture, this method is designed to particularly cope with blurred and unfocused iris images. Global variations extract a general presentation of texture, while local yet soft variations encode texture details that are minimally reliant on the image quality. Discrete Cosine Transform and wavelet decomposition are used to capture the local and global variations. In the matching phase, a support vector machine fuses similarity values obtained from global and local features. The verification performance of the proposed method is examined and compared on CASIA Ver.1 and UBIRIS databases. Efficiency of the method contending with degraded images of the UBIRIS is corroborated by experimental results where a significant decrease in FRR is observed in comparison with other algorithms. The experiments on CASIA show that despite neglecting detailed texture information, our method still provides results comparable to those of recent methods.
Highlights
High level security is a very complicated predicament of contemporary era
We proposed a new feature extraction method based on the local and global variations of the iris texture
Experimental results on the UBIRIS database showed that the authentication performance of the proposed method is superior to that of other recent methods
Summary
Dealing with issues like border-crossing security, restricted areas access control, warding off terrorist attacks, and information security is critically essential in modern societies. Traditional methods like password protection or identification cards have run their courses and nowadays are regarded suboptimal. The need for eliminating the risk of such identification means has been shifting researchers’ attention to unique characteristics of human biometrics. Being stable over the lifetime and known as a noninvasive biometric, the human iris is accepted as one of the most popular and reliable identification means, providing high accuracy for the task of personal identification. Surrounded between the pupil and the white sclera, the iris has a complex and stochastic structure containing randomly distributed and irregularly shaped microstructures, generating a rich and informative texture pattern in the iris
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
