3 D Face Expression Recognition

Facial expressions contain various information which represent human behaviors. It is an important way to express moods and an effective way to communicate with each other without language. People can judge others’psychological behaviors by recognizing their facial expressions. Human expressions equal7%language performance,38%sound performance and55%facial expressions. Study on recognizing facial expressions becomes a hot spot in fields of pattern recognition and artificial Intelligence. Due to the development of3D scanning technique and multi attitudes on recognizing2D facial expressions, an increasing number of researchers pay attention to3D facial expressions recognition, and researchers have made great advances on this in recent years. This paper also does some research in this field.Face expressions recognition system generally includes image data preprocessing, feature extraction, expression classification. This article does its exploratory research in the following four aspects:The goal of this paper is to design an automatic facial expressions recognizing system, so this paper collected original data to identify facial expressions directly. Moreover, it does not require any manually labeled landmarks. Feature extraction and expression identification are both accomplished by computer.During the process of data preprocessing, each original scan of3D point cloud data preprocessing are sheared, smoothed, filled holes, coordinated, and aligned grids to get normalized cloud data.After data preprocessing feature extracting is accomplished, this paper extracts curvature based feature information of3D facial expression.3D facial expression recognition use four curvature based shape descriptors who offer more information of facial features over3D representation:the principal curvature kl, k2, Mean curvature, Shape Index. Then encoding the curvature information employs Local Curvature Patterns (LCPs) which is akin to the approach LBP. In the process of identifying facial expression, Chi-square distance is compared with SVM classifier for identifying six basic expressions.The test indicates that the algorithm recognition average recognition rate achieves80.31%. The results demonstrate that our algorithm is effective. In addition, we propose some protocols based on current public3D face databases of facial expression recognition, gender classification, ethnicity classification and age estimation.