Research on Face Recognition Algorithm Based on LBP and DT-SVM Decision Tree

Abstract

In order to improve the recognition rate of face recognition, an improved face recognition algorithm is proposed. The algorithm first applies the basic principle of the local two valued model (LBP), the LBP feature histogram sequence is taken as the basic feature of the face, and then, basically, the original SVM decision algorithm (DT - SVM) is used. In this paper, an improved SVM decision tree algorithm is proposed. Finally, face recognition experiments are carried out in face database, and the experimental results are analyzed.