The Application Of Face Recognition In Security Robot And Occluded Face

In this paper,we first present a real-time face recognition system for home security service robot which can be applied to identify the identity of a person in front and give a warning when the identity of the person is a stranger.Considering the complexity of the actual situation,there might be some errors causing by the following factors like the angle,the size,the environment and the illumination of the human face,which can hardly be avoided.Our system is designed to reduce and eliminate the influence of the factors above.More specifically,we first use Local Binary Patterns(LBP)to detect face and then cut out the face region.With the collected face database pretreated,we can recognize the face that has been detected based on Support vector machine(SVM).However,the given face images are always Irregular in size,face's position,scale and some other factors.The alignment for face database in this paper is based on the eye location.The proposed face recognition system has been tested in practical application for home security service robot.The results indicate that our face recognition system is effective and real-time.It works well in multi-face recognition and Identify strangers,which meet the demand of robot.The second part is an occluded face recognition system based on the Convolutional Neural Network(CNN),especially when some key parts of a face image part are obscured,it is more difficult to identify the identity of the man.CNN is now a common algorithm in Deep Learning,The convolution neural network used in face recognition effect is ideal,in the process of experiment,we found that the CNN is strong robustness,and when it is applied to the face recognition with occlusion,it achieves better results than many classic face recognition algorithm.