An efficient iris segmentation model based on eyelids and eyelashes detection in iris recognition system

摘要

This paper presents an efficient noise reduction scheme to remove localized high frequency information from segmented iris region for personal authentication based on radial suppression. Eyelash and eyelids of localized iris area is considered as noisy information. Accuracy of iris recognition system generally depends on accurate segmentation and noise deduction. Proposed method not only removes eyelash and eyelids by suppressing localized frequency using radial suppression but also detects the pupil and iris center accurately as well as localizes the iris and pupil region. Finally, this paper also designates a prototype of automated iris recognition system for personnel authentication. For iris feature extraction purpose, one dimensional Log Gabor wavelet has been used where the feature vector length has been reduced without less loss of Information. It has also been showed here that the proposed detection model has a stable matching score. The proposed automated iris recognition system with maximum suppression of eyelashes has less equal error rate which indicates the superiority of the performance compared to the other existing methods.