tailieunhanh - Báo cáo hóa học: "Research Article A Novel Retinal Identification System"

Tuyển tập báo cáo các nghiên cứu khoa học quốc tế ngành hóa học dành cho các bạn yêu hóa học tham khảo đề tài: Research Article A Novel Retinal Identification System | Hindawi Publishing Corporation EURASIP Journal on Advances in Signal Processing Volume 2008 Article ID 280635 10 pages doi 2008 280635 Research Article A Novel Retinal Identification System Hadi Farzin 1 Hamid Abrishami-Moghaddam 1 and Mohammad-Shahram Moin2 1 Department of Electrical Engineering . Toosi University of Technology Seyed Khandan 16315-1355 Tehran Iran 2 Iran Telecommunication Research Center North Kargar 14399-55471 Tehran Iran Correspondence should be addressed to Hamid Abrishami-Moghaddam moghadam@ Received 1 May 2007 Revised 27 December 2007 Accepted 21 February 2008 Recommended by Nikolaos V. Boulgouris This paper presents a novel biometric identification system with high performance based on the features obtained from human retinal images. This system is composed of three principal modules including blood vessel segmentation feature generation and feature matching. Blood vessel segmentation module has the role of extracting blood vessels pattern from retinal images. Feature generation module includes the following stages. First the optical disk is found and a circular region of interest ROI around it is selected in the segmented image. Then using a polar transformation a rotation invariant template is created from each ROI. In the next stage these templates are analyzed in three different scales using wavelet transform to separate vessels according to their diameter sizes. In the last stage vessels position and orientation in each scale are used to define a feature vector for each subject in the database. For feature matching we introduce a modified correlation measure to obtain a similarity index for each scale of the feature vector. Then we compute the total value of the similarity index by summing scale-weighted similarity indices. Experimental results on a database including 300 retinal images obtained from 60 subjects demonstrated an average equal error rate equal to 1 percent for our identification system. .