Novel iris segmentation and recognition system for human identification

The richness and apparent stability of the iris texture make it a robust biometric trait for personal authentication. The performance of an automated iris recognition system is affected by the accuracy of the segmentation process used to localize the iris structure. In case of wrong segmentation, wrong features will be extracted and hence, may lead to false identification results. Most of the authors propose Circular Hough Transform to localize the boundary of IRIS. But the problem with this technique is its high consumption of time and memory. It also requires a precise estimated range of the boundary and it fails to localize the IRIS if the correct estimation is not provided. The proposed technique follows a basic strategy and obtains the major boundaries, by using canny edge detector. Features have been extracted using Curvelets Transform; Principal Component Analysis is then used to reduce the dimension of the features. Then SVM has been used as classifier. The implementation of recognition method has shown encouraging results.