Extraction of Dual Tree Complex Wavelet Feature for IRIS Recognition

Abstract: Biometrics is the science and technology of measuring and analyzing biological data. In Information technology, biometrics refers to technologies that measure and analyzes human body characteristic such as DNA, finger prints, eye retinas and irises for authentication purposes. Biometrics is used in computer science for the identification and access control. A novel descriptor for iris recognition is proposed by using dual-tree complex wavelet feature and Support Vector Machine (SVM). The approximate shift invariant property of the dual tree complex wavelet and directional selectivity in 2D makes it an ideal choice for iris recognition. SVM is used as a classifier and some kernel functions are tested in the experiment. The obtained result showed that the proposed approach enhances the classification accuracy. In this experimental results were also compared with the k-NN and Naïve Bayes classifier to demonstrate the efficiency of the proposed technique.

Keywords: Biometrics, IRIS boundary, IRIS recognition, Support Vector Machine (SVM), Feature Extraction, Hamming Distance, Dual tree complex wavelet transform