Improving the Performance of Iris Recogniton System Using Eyelids and Eyelashes Detection and Iris Image Enhancement

Abstract

Iris recognition gets more and more attention for its high accuracy rate. However, the iris images are often occluded by eyelids and eyelashes partly and if these noises can't be removed the performance of iris recognition system will be degraded badly. On the other hand low contrast and non-uniform brightness will also increase the difficulty of feature extraction and matching. In this paper an efficient method for eyelids and eyelashes detection and iris image enhancement is described which includes two parts mainly. In the first part, eight eyelids/eyelashes models are presented and different model corresponds to different eyelids and eyelashes type. The real eyelids/eyelashes areas can be detected by comparing the variation of every sub-block of each eyelids/eyelashes model. The second part is iris enhancement, in this part the background illumination of the normalized iris image is estimated and subtracted from it. Then histogram equalizing and viener filtering are implemented to enhance the normalized iris image. In order to evaluate the necessity of this method an iris recognition algorithm based on 1D gabor filter is developed and results are encouraging in CASIA 1.0 iris images sets.