Partial iris feature extraction and recognition based on a new combined directional and rotated directional wavelet filter banks

Abstract

This paper presents a novel approach to construct two-dimensional (2-D) non-separable, non-redundant, multiscale combined directional wavelet filterbank (CDWFB) for iris feature-extraction. This CDWFB is obtained by the combination of directional wavelet filterbank (DWFB) and rotated directional wavelet filterbank (RDWFB). Firstly, 2-D biorthogonal wavelet filterbank (BWFB) is designed based on the factorization of a general half-band polynomial. Secondly, McClellan transformation is used to obtain checkerboard shaped filterbank (CSFB) using designed BWFB coefficients. This CSFB is applied on 2-D BWFB to obtain DWFB. RDWFB is obtained using DWFB coefficients whose directions are 45° apart from DWFB. Iris recognition systems are still incapable for providing low false rejection and significant representation. In order to address these problems, a novel approach is proposed to extract iris texture in twelve-directions by CDWFB. The inner half-iris region (partial iris) is divided into six non-overlapping sub-regions and selected four-regions for further processing to derive compact and significant iris-features. An independent feature extraction using CDWFB is carried out on each region. The dissimilarity measure of each region are fused at the decision level by exploring 1-out-of-n: Accept (A) post-classifier in order to reduce the false rejection rate. Experimental results using UBIRIS and MMU1 databases show the superiority of the proposed method with some of the popular iris recognition algorithms.