An Efficient One-Dimensional Fractal Analysis for Iris Recognition

Teo,Ch.Ch., Ewe,H.T.

Abstract:
An iris recognition system is proposed in this paper. This system implements (a) the combination of proposed black hole search method and integro-differential operators for iris localization, (b) one-dimensional fractal analysis for feature extraction and (c) dissimilarity operator for matching. The black hole search method achieves 100% accuracy of pupil detection for both CASIA and MMU Iris databases. Experiment results show that the proposed system has an encouraging result with low EER in CASIA iris database and in MMU iris database. It provides an alternative solution for iris recognition and acts as a spring board for further investigation.