Uniform Local Binary Patterns Approach For Human Facial Expression Recognition

Résumé: facial expression analysis is rapidly becoming an area of intense interest in computer science and human computer interaction design communities. Psychological studies have suggested that facial motion is fundamental to the recognition of facial expression. Expression is the most important mode of non-verbal communication between people. Recently, the facial expression recognition technology attracts more and more attention with people’s growing interesting in expression information. In this paper, we propose LBP histograms based automatic facial expression recognition system to recognize the human facial expression like happy, fear, sad, angry, disgust and surprise. Initially facial image is segmented into three region from which the uniform local binary patterns (LBP) texture features distributions are extracted and represented as a histogram description. A Support Vector Machine is used to classify different kinds of facial expressions. We have carried our experiments upon Yale face database and JAFFE face database. The Yale Face Database contains 165 grayscale images in GIF format of 15 individuals. JAFFE Database, available at http://www.kasrl.org/jaffe.html consisting 213 images posed by 10 Japanese female models. The proposed model reports 92.53% of classification accuracy.

Publié dans la revue: