Iris Recognition for Biometric Personal Identification Using Neural Networks.
ABSTRACT This paper presents iris recognition for personal identification using neural networks. Iris recognition system consists of localization of the iris region and generation of data set of iris images and then iris pattern recognition. One of the problems in iris recognition is fast and accurate localization of the iris image. In this paper, fast algorithm is used for the localization of the inner and outer boundaries of the iris region. Located iris is extracted from an eye image, and, after normalization and enhancement it is represented by a data set. Using this data set a neural network is applied for the classification of iris patterns. Results of simulations illustrate the effectiveness of the neural system in personal identification.
Conference Paper: Adaptive Iris Segmentation.[Show abstract] [Hide abstract]
ABSTRACT: In this paper an adaptive iris segmentation algorithm is presented. In the proposed algorithm Otsu Threshold value, average gray level of the image, image size, Hough-Circle search are used for adaptive segmentation of irises. Otsu threshold is used for selecting threshold value in order to determine pupil location. Then Hough circle is utilized for pupillary boundary, and finally gradient search is used for the limbic boundary detection. The algorithm achieved 98% segmentation rate in batch processing of the CASIA version 1 (756 Images) and version 3 (CASIA-IrisV3-Interval, 2655 Images) databases.Advances in Information Security and Assurance, Third International Conference and Workshops, ISA 2009, Seoul, Korea, June 25-27, 2009. Proceedings; 01/2009