Efficient iris recognition via ICA feature and SVM classifier

With the increasing demands of security in ournet worked society,the technology for personalidentification works as the main solution to safe-guard people s properties.Biometrics is an alterna-tive to solve the problemand has the advantage thatthey cannot be stolen or forgotten like pass words.Because personal identification numbers or identifi-cation tokens(such as s mart cards)cannot provide ahighlevel of security which can be copied,inspec-ted and/or stolen.They only showthe knowledgeof som…

Efficient iris recognition via ICA feature and SVM classifier

To improve flexibility and reliability of iris recognition algorithm while keeping iris recognition success rate, an iris recognition approach for combining SVM with ICA feature extraction model is presented. SVM is a kind of classifier which has demonstrated high generalization Capabilities in the object recognition problem. And ICA is a feature extraction technique which can be considered a generalization of principal component analysis. In this paper, ICA is used to generate a set of subsequences of feature vectors for iris feature extraction. Then each subsequence is classified using support vector machine sequence kernels. Experiments are made on CASIA iris database, the result indicates combination of SVM and ICA can improve iris recognition flexibility and reliability while keeping recognition success rate.