Survey of Iris Image Segmentation and Localization

Abstract

Iris recognition is one of the best methods in the biometric identification field because the iris has features that are not unique but also stay throughout the person’s lifetime. Iris recognition has multiple phases namely Image Acquisition, Iris Segmentation, Iris Localization, Feature Extraction and Matching. Image Acquisition is simply the capturing of the iris image at an optimal distance. Iris Segmentation is the process of obtaining all the different segments of the eye. Iris Localization is the process of finding inner and outer boundaries of the iris differentiating it from the sclera and pupil and mainly focusing on the iris alone. Feature extraction is the process of extracting the biometric template from the Iris, giving the unique data required for the next step. Matching is the process of finding the best match in the database for the extracted biometric template. The future implementation of this paper focuses only on the processes of Image Acquisition, Iris Segmentation and Iris Localization. The paper aims to optimise these processes in terms of image capture distance, computation time and memory requirement, using the Dynamic Reconfigurable Processor (DRP) technology along with suitable algorithms for segmentation and localization processes as described in sections 2.2 and 2.3 respectively.