Tuyển tập các báo cáo nghiên cứu về sinh học được đăng trên tạp chí sinh học Journal of Biology đề tài: Research Article Robust Iris Verification Based on Local and Global Variations | Hindawi Publishing Corporation EURASIP Journal on Advances in Signal Processing Volume 2010 Article ID 979058 12 pages doi 2010 979058 Research Article Robust Iris Verification Based on Local and Global Variations Nima Tajbakhsh 1 Babak Nadjar Araabi 1 2 and Hamid Soltanian-Zadeh1 2 3 1 Control and Intelligent Processing Center of Excellence School of Electrical and Computer Engineering University of Tehran Tehran 1439957131 Iran 2School of Cognitive Sciences Institute for Research in Fundamental Sciences IPM Tehran 1954856316 Iran 3 Radiology Image Analysis Laboratory Henry Ford Health System Detroit Michigan 48202 USA Correspondence should be addressed to Hamid Soltanian-Zadeh hszadeh@ Received 22 December 2009 Revised 28 April 2010 Accepted 25 June 2010 Academic Editor Jiri Jan Copyright 2010 Nima Tajbakhsh et al. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use distribution and reproduction in any medium provided the original work is properly cited. 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 extraction method 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 .
