Shift Invariant Iris Feature Extraction Using Rotated Complex Wavelet and Complex Wavelet for Iris Recognition System

Abstract

In this paper, authors have proposed a novel approach of  feature extraction of iris images using combination of  2D Dual Tree Rotated Complex Wavelet Transform (RCWT) and 2D Dual Trace Complex Wavelet Transform(CWT). This method provides features in 12 directions against 3 and 6 directions in DWT and CWT respectively. Iris features are obtained by computing  energies and standard deviation of detailed coefficients in 12 directions per stage, at 3 levels of decomposition. Canberra distance is used for matching. The results are obtained using DWT, CWT combination of CWT and RCWT on UBIRIS database of 2400 images. The performance measure, ZeroFAR, is reduced from 6.3 using DWT to 2.7 using proposed method. The method is also computationally efficient as compared to Gabor Filters.