Multispectral iris recognition utilizing hough transform and modified LBP

Abstract

This paper presents a multispectral iris recognition scheme using Circular Hough Transform (CHT) and a modified Local Binary Pattern (mLBP) feature extraction technique. The CHT is used to localize the iris regions from the multispectral iris images. We also apply the binary thresholding and edge detection techniques in an effort to reduce the effects of over and under segmentation in multispectral iris images in which iris and pupil boundaries are not clearly separable. Furthermore, we apply mLBP in an attempt to elicit the iris feature elements. The mLBP technique combines both the sign and magnitude features for the improvement of iris texture classification performance. The identification and verification performance of the proposed scheme is validated using a multispectral iris dataset of 3120 images.