A new matching approach for local feature based iris recognition systems
Chung-Chih Tsai, Heng-Yi Lin, J.S. Taur, Chin‐Wang Tao · 2010
Traditional iris recognition systems can achieve excellent performance in both verification and identification. However, most of the existing systems adopted a similar technique to deal with the iris image. In this paper, we propose a novel matching strategy with invariant properties, which is based on the possibilistic fuzzy clustering algorithm, to compare a pair of local feature sets. Moreover, an efficient iris segmentation method is proposed to detect the inner and outer boundaries of the iris from a gray-level image and isolate the annular iris region. For feature extraction, the Gabor filters are adopted to detect the local feature points from the segmented iris image in the Cartesian coordinate system and generate a rotation-invariant descriptor for each detected point. After that, the proposed matching algorithm is used to compare two sets of feature points and compute a similarity score for a pair of iris images. Experimental results show that the performance of the proposed approach is comparable to that of the well-known iris recognition systems.