On the performance improvement of non-cooperative iris biometrics using segmentation and feature selection techniques

Abstract

In this work, an improved segmentation methodology and a novel statistical dependency-based backward feature selection algorithm are proposed. From the input eye image, iris boundary is identified using Circular Hough Transform. A bounding box is defined using the radius obtained followed by iterative thresholding techniques to eliminate specular reflections, eyelids, eyelashes and pupil region. First-order and second-order statistical features are extracted from the segmented iris. For the first time, the statistical measure, Chi-square value is computed from GLCM as a new novel feature from iris images. Statistical dependency-based backward feature selection (SDBFS) algorithm is used to reduce the feature vector size. By operating on local features in reduced search space, computation complexity of segmentation is reduced with less mislocalisation count and eliminates pupil dilation effects. Results of SDBFS show the usefulness of minimal-useful features. Experimental results conducted on CASIA V1, V3-interval and UBIRIS V1 datasets show that statistical features in non-ideal iris images outperform some of the state-of-the-art methods.