Research On Facial Expression Based On Face Recognition Technology

Facial expression contains human complex inner feeling which is an important way to communicate among persons.In recent years,it has become the focus of research in many fields such as computer vision,human-computer interaction,pattern recognition,and so on.The realistic meaning of facial expression recognition is to make the computer act according to the human’s "face",so that the computer can understand the idea of human beings,and it is more intelligent,at the same time,a more natural human-computer interaction process is obtained.In general,expression recognition system consists of four parts: get the samples of expression image,image processed,feature extraction and classification.Among them,feature extraction and feature classification are the core technologies of expression recognition.The expression have low recognition rate.So this paper proposes a novel expression method based on LBP partition and IWO-ELM,The main work of this paper is as follows:Firstly,in order to eliminate some interference conditions such as uneven illumination,a expression image acquisition device is designed.Secondly,face recognition and feature extraction.On the basis of Ada Boost face detector,combined with Open CV database to identify the face image.This part analyzed several typical feature extraction algorithms,the method of LBP was used as the feature extraction method according to its advantage in texture extraction.Finally,features classification.This paper chooses IWO-ELM to classify the features of expression images.The training samples are used to train expression model.The test samples are used to calculate and estimate.There are three databases used in the experiment,JAFFE databases,CASME databases and collected image.Then,a large number of experiments are carried out to verify the performance of the method used in this paper.Experiments proved that the algorithms used in this paper have achieved satisfactory results.