The Research On Key Technology Of Multimodal Biometric Authentication

Biometrics authentication technology is an emerging technology in recent years, which has unique advantages over traditional authentication technology and is widely used in finance,public security areas and also in daily life.This paper focuses on both face and voice biometric algorithms and their support vector machine (SVM) fusion algorithm under verification mode and the main content is as follows:First of all,due to the problem that face recognition technology is not able to guarantee real-time in practical applications with a huge number of clients,face verification algorithm based on feature face verification algorithm are studied.Above all, individual eigenface subspaces are constructed for each subject,under which there are more samples in different illumination,facial expressions and pose situations.Then, through the introduction of four kinds of classifier,namely the Euclidean distance, Mabalanobis distance, reconstruction error and normalized correlation coefficient, to classify the result of the sample. In the end, fusion is conducted on the score matching level with generalized discriminant analysis (GDA).Classified by the result of the experiment found that feature face algorithm based on the pattern of confirmation, the strong robustness to the various changes. Classifier to classify with reconstruction error, among all the comparison of the classifier, the performance is the best. Fusion can further improve the performance, compared to the same kind algorithm, has a certain advantage.Second,text-independent speaker verification is based on Gaussian mixture model,which employs linear combination of dozens of single Gaussian probability density function to describe the distribution of speaker’s voice feature and overcome shoft-session test problem.In the experiment,only durations of0.20s and0.52s speech sessions afe used for test and small equal error rates are obtained.In the end,a hybrid personal identity authentication strategy with flexible security levels is proposed after combining traditional personal identity technology and biometric technology.