The Removal of Specular Reflection in Noisy Iris Image

Abstract

Iris recognition is a biometric system that uses human iris features to determine and verify the identity of human. Other biometric systems are fingerprint, face, ear, voice, gait, blood vessels and many more. A complete iris recognition system includes: iris acquisition, iris segmentation, feature extraction and matching. The main factor to obtain high segmentation and recognition accuracy is the quality of iris pattern. The quality of iris pattern can be affected because of specular reflection. Specular reflection happens during iris acquisition and it can reduce the features of iris pattern. This work is significant since the improved iris pattern can enhance the performance of iris localization, iris segmentation and feature extraction in the iris recognition system. In this paper, the iris image enhancement methods are proposed to remove the specular reflection. UBIRIS v1 and CASIA v4 databases are used for testing. Based on the results, the proposed methods managed to remove the specular reflection without affecting the iris image quality. The proposed methods also obtained fast execution time and low memory