Extraction and Recognition of Iris Features Based on KPCA and SVM
You Wu · Journal of Chongqing Institute of Technology · 2009
A new method for iris feature extraction and recognition is proposed in this paper.Firstly,the kernel principal component analysis(KPCA) is used to extract iris texture feature of a strong ability to extract features.In order to reduce the samples of the SVM,two-layer serial classifier is designed,which combines SVM and distance classification,and a rejecting coefficient and rejecting rule are defined.According the rejecting rule,the classifier can classify the irises and give the final results,or reject to classify.The rejected iris images are fed into SVM for further classification.The classification algorithms can take advantage of SVM and distance classification.Experimental results show that the method has high speed and high iris recognition rate.