Research On Algorithm Of Facial Expression Recognition And Its Applications

Facial expression recognition is one of the most challenging problems in the fields of biometric identification, image processing, machine vision, movement tracking, pattern recognition, physiology and psychology, and it has become a hot research topic in the filed of pattern recognition and artificial intelligence in recent years. Facial expression recognition is an important part of affective computing and intelligent human-machine interactive, which has a wide range of applications and potential market value.Facial expression recognition consists of such modules as face detection, feature extraction, feature selection and expression classification. In this paper, feature extraction and expression classification are studied.Several improved algorithms and methods for these tasks are developed. The performances of our methods are illustrated by simulation experiment results.The major contributions of this paper are as follows.1. In section of facial feature exrtraction:Classical Active Shape Model (ASM) is studied including shape matching algorithm based on gray-level.Some factors which impact ASM searching are conducted and analyzed.Two improved methods are proposed:(1)Locate rough position of eyes using PCDM. Then a good initial positon can be got according to the characteristics of human face images, which can decrease the failure searching of ASM(2)Local appearance model is constructed with the local information of neighboring landmark and gray level information of feature.2. In section of facial expression automatic classification:Classical AFSA is studied.Some factors which impact AFSA are conducted and analyzed.Two improved methods are proposed:(1)Best-step operator. This paper proposes the best-step operator to avoild the impacts of the random step in classical AFSA.(2)The prey behavior played a very important role in AFSA. The improved prey behavior not only extends the search scope, but also uses the information has been got.(3)An improved artificial fish-swarm algorithm for the RBF neural network and a model based on this method is developed.Finally, the new algorithm is applied to the problem of expression recognition combind with ASM. The research indicates that the new algorithm has some advantages in terms of convergence performance, recognition rate and so on.