Authors: S. Arivazhagan, L. Ganesan, T. Srividya
Addresses: Department of Electronics and Communication Engineering, Mepco Schlenk Engineering College, Sivakasi 626 005, India. ' Department of Computer Science Engineering, Alagappa Chettiar College of Engineering & Technology, Karaikudi 623 004, India. ' Department of Electronics and Communication Engineering, Mepco Schlenk Engineering College, Sivakasi 626 005, India
Abstract: Iris recognition is one of the most reliable personal identification methods and it plays a very important role in forensic and civilian applications. In this paper, an efficient multi-resolution based iris recognition system with high performance and less complexity is described. The system includes pre processing iris images, determining the pupil centre, converting the iris boundary to the stretched polar coordinate system, extracting the iris code based on texture analysis using multi-resolution transforms, such as Discrete Wavelet Transform (DWT), Double Density Wavelet Transform (DDWT) and Dual Tree Complex Wavelet Transform (DTCWT). A fast matching scheme based on exclusive OR operation to compute the similarity between a pair of position sequences in iris code is used for classification.
Keywords: biometrics; normalisation; multi-resolution transforms; feature extraction; iris code; iris recognition; wavelet transforms; eyes; personal identification.
International Journal of Biometrics, 2009 Vol.1 No.3, pp.254 - 267
Published online: 30 Mar 2009 *Full-text access for editors Access for subscribers Purchase this article Comment on this article