Robust iris recognition with region division

In this paper, we propose an efficient and fast feature extraction method for iris recognition using the wavelet transform. A major problem of iris recognition is that noises such as the eyelid, eyebrow and glint may be included in iris images, and such noises adversely affect the performance of iris recognition systems. In order to solve these problems, we propose to divide the iris texture image into several sub-regions and apply the wavelet transform separately to each sub-region. Furthermore, we discard some sub-regions which have large differences to exclude potential noises. Experimental results show that the performance of the proposed method is comparable to that of the method using the Gabor transform and that region division noticeably improves recognition performance. It is further noted that the processing time of the proposed method is much faster than the Gabor transform.