IMPROVING EFFECTIVENESS IN IRIS LOCALIZATION USING ACTIVE CONTOURS WITH LESS COMPUTATIONAL TIME

Human identification through iris recognition has been acknowledged as one of the most accurate biometric modalities because of its high recognition rate. Generally, the process of iris recognition consists of six subcomponents, viz. iris localization, iris segmentation, normalization, iris feature extraction, and matching.In order to provide successful iris recognition, iris localization plays a major role. In the present study, we compare Daugman, Wildes and Cui and R P Ramkumar methods for Iris localization. The most difficult part in iris identification system is the iris localization. The iris is the colorful part of the eye that surrounds the pupil; it defines the inner and outer boundaries of iris region used for feature analysis. Several researches have been made in the subject of segmentation and iris finding. The efficiency of the algorithms can be increased if the inner boundary and outer boundary of iris are detected accurately and also the computational cost will be reduced. This paper mainly focuses on iris localization process. Section 2 deals with overview of existing iris localization Algorithms and their comparison. Then Section 3 insists on the proposed method. In this proposed iris localization method, a segmentation techniques is used based on active contours which is 100 % accurate compared to Daugman, s integro-differential method. For iris outer boundary detection, contrast enhancement, special wedges, and thresholding are employed to detect the specific iris regions from an eye image, which is capable of almost completely eliminating the geometry-based distortion of defected iris data for any human subject