Recognition of Facial Expressions by Extracting Local Binary Pattern Features

People’s facial expressions play an important role in social relations, and as a result automatic recognition of facial expressions has attracted great attention from behavioral sciences. However, automatic recognition of facial expressions is a difficult and complicated process because the similarities among different expressions will result in wrong identification of facial expression in this process. For instance, in both cases of happiness and surprise, the mouth is open, thus there is a chance of misinterpreting these two expressions. In this study, we want to extract the features of facial expressions from Cohn Kanade database by using Local binary pattern method, and improve the result of facial expression recognition. To achieve this goal and to identify these features, we assess learning methods of a machine such as: Support vector machine, Linear Discriminant Analysis and template matching, which the best result was gained through the support vector machine classifier. In this paper, we reached an above 97% rate in , Support vector machine classifier by assessing 10 folds and Kernel function of Radial basis function. This precision percentage is very desirable compared to aforementioned learning machine methods.

Keywords:

Facial expression recognition , Local binary pattern , Support vector machine , template matching , Linear Discriminant Analysis