Multi-class SVM based iris recognition

We propose an improved iris recognition method to identify the person accurately by using a novel iris segmentation scheme based on the chain code and the collarette area localization. The collarette area is isolated as a personal identification pattern, which captures only the most important areas of iris complex structures, and a better recognition accuracy is achieved. The idea to use the collarette area is that it is less sensitive to the pupil dilation and usually not affected by the eyelids or the eyelashes. The deterministic feature sequence is extracted from the iris images using the 1D log-Gabor wavelet technique and used to train the support vector machine (SVM) as iris pattern classifiers. The parameters of SVM are tuned to improve the overall system performance. Our experimental results also indicate that the performance of SVM as a classifier is far better than the performance of backpropagation neural network (BPNN), K-nearest neighbor (KNN), Hamming distance and Mahalanobis distances. The proposed innovative technique is computationally effective as well as reliable in term of recognition rate of 99.56%.