Abstract
Most of the prominent features of human face are present in the ocular area, referred as the periocular region. Complex and dense features in these regions makes it a candidate to be used as a biometric trait. This paper discusses an effective method for periocular recognition using non-overlapped blockwise interpolated local binary pattern (iLBP) features. For a given periocular image, an iLBP coded feature image is obtained and further divided into four equal non-overlapping sub-regions. From each sub-region having iLBP pattern, eight bin histogram features are calculated. A single feature vector is formed by concatenating blocked histograms of each non-overlapping region. Binned histogram based feature is also extracted using Phase Intensive Global Pattern (PIGP) features for comparison of results. Experiments are conducted on UBIRIS.v1 and UBIPr.v2 datasets. From the experiments, it is observed that selected histogram feature bins through the proposed approach provide a more compact representation of periocular image and size of the feature vector is also reduced with significant improvement in performance.
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.
