Improved Support Vector Machine Algorithm (SVM) For Biometric Data Classification

With the rapid development of computer science and Internet technology,biometric technology is widely used in our social life,such as fingerprint recognition,face recognition and so on.As the face recognition has mandatory,contact and so on,and,as a biometric technology,face recognition method quickly become an important research area.Face recognition is a hot topic in pattern recognition.Face recognition is widely used in authentication,detection,and investigation of safety requirements of high places because of its convenience.Face recognition algorithm developed from the initial simple conditions of the identification to the identification of multiple factors under complex conditions.Face recognition in multiple factors in light,face rotation,face occlusion,noise pollution,skin color,and race factors are the factors to be considered in face recognition.Face recognition under the complex condition is still a difficult problem in the field of face recognitionIn this research,we study the problem of biometric data classification.The biometric data classification using support vector machine algorithm is widely used but the recognition takes a long time.To decrease running time,dimensionality reduction is normally adopted.Dimensionality reduction is preprocessing step before importing data to the algorithm used in the classification step.In the past,many researchers have proposed techniques for the classification of biometric data using dimensionality reduction techniques and most of them are used with face image data.Model accuracy is the only performance measure metric.Di?mensionality reduction can be applied to several kinds of biometric data and then compare the classification time.This scheme is however complex.As a result,the research work of this kind rarely appear.We thus propose in this research the improvement of support vector machine algorithm for biometric identification called the Bio-SVM algorithm.The main objectives are to increase efficiency and reduce the time for data classification.We apply a linear discriminant analysis(LDA)as a dimensionality reduction technique.Then,we use LDA with the algorithm support vector machine using a linear kernel function for physio-logical biometric image identification and use support vector machine using the polynomial function for behavioral biometric image identification.Then implementation and experi--mentation have been done with the Python language.This research uses accuracy and time as a measurement to evaluate the performance of biometric data classification.