Abstract: In this paper, a new expression recognition approach is presented based on cognition and mapped binary patterns. At first, the approach is based on the LBP operator to extract the facial contours. Secondly, the establishment of pseudo 3D model is used to segment face area into six facial expression sub-regions. In this context, the sub-regions and the global facial expression images use the mapped LBP method for feature extraction, and then use two classifications which are the support vector machine and softmax with two kinds of emotion classification models the basic emotion model and the circumplex emotion model. At last, we perform a comparative experiment on the expansion of the Cohn-Kanade (CK +) facial expression data set and the test data sets collected from ten volunteers. The experimental results show that the method can effectively remove the confounding factors in the image. And the result of using the circumplex emotion model is obviously better than the traditional emotional model. By referring to relevant studies of human cognition, we verified that eyes and mouth express more emotion.

Facial expression analysis is a remarkable and demanding problem, and impacts significant applications in various fields like human-computer interaction and data-driven animation. Developing an efficient facial representation from the original face images is a crucial step for achieving facial expression recognition. Facial representation based on statistical local features, Local Binary Patterns (LBP) is practically assessed. Several machine learning techniques were thoroughly observed on various databases. LBP features- which are effectual and competent for facial expression recognition are generally used by researchers Cohn Kanade is the database for present work and the programming language used is MATLAB. Firstly, face area is divided in small regions, by which histograms, Local Binary Patterns (LBP) are extracted and then concatenated into single feature vector. This feature vector outlines a well-organized representation of face and is helpful in determining the resemblance among images.

Keywords: Binary pattern, Facial Expression, Gausian Filter, Recognization.

| DOI: 10.17148/IJIREEICE.2020.8629