Performance Analysis of Segmentation Techniques for Iris Recognition System

Abstract

A biometric system provides automatic identification of an individual based on a unique feature or characteristic possessed by the individual. Iris recognition is regarded as the most reliable and accurate biometric identification system available. Iris recognition systems capture an image from an individual's eye. The iris in the image is then segmented and normalized for feature extraction process. The performance of iris recognition systems highly depends on segmentation and normalization. For instance, even an effective feature extraction method would not be able to obtain useful information from an iris image that is not segmented or normalized properly. This thesis is to enhance the performance of segmentation and normalization processes in iris recognition systems to increase the overall accuracy. The iris recognition system based on the Daugman’s integrodifferential equation and Hough transform is implemented. The system is able to localise the circular iris and pupil region, occluding eyelids and eyelashes, and reflections. The extracted iris region was then normalised into a rectangular block with constant dimensions to account for imaging inconsistencies. Finally, the phase data from one-dimensional log-Gabor filters was extracted and quantised to four levels to encode the unique pattern of the iris into a bit-wise biometric template. The Hamming distance was employed for classification of iris templates, and two templates were found to match if a test of statistical independence was failed. The previous iris segmentation approaches assume that the boundary of pupil is a circle. However, according to our observation, circle cannot model this boundary accurately. To improve the quality of segmentation, a novel active contour method based on Level Set Evolution without re-initialization is proposed to detect the irregular boundary of pupil. The method can successfully detect all the pupil boundaries in the CASIA database and increase the segmentation accuracy by almost .