Region-based feature extraction from non-cooperative iris images using CDF 9/7 filter bank

摘要

In this paper, the authors have investigated the iris feature extraction technique using Cohen-Daubechies-Feauveau 9/7 (CDF 9/7) filter bank. Most of the iris recognition systems have been found to give near perfect performance in constraint environment. Unfortunately, the accuracy falls drastically when the constraints are relaxed during image acquisition process. These include dilation of pupil, occlusion due to eyelids and eye lashes, and most importantly non-orthogonal view of iris. These factors result in reduced accuracy of the overall system. In this work, a technique has been proposed to deal with segmentation failure and occlusion. The experimental studies deal with the superiority of CDF 9/7 filter bank over the frequency-based techniques.