基于机器人视觉的服务机器人表情识别研究

Research on Service Robot Oriented Facial Expression Recognition Based on Vision

开发了一种基于机器人视觉的表情识别系统。系统首先基于人脸肤色及Gabor纹理特征精确定位人脸区域,其次用Gabor小波变换提取表情特征并设计基于支持向量机的表情分类器,最终实现对7种人脸基本表情的识别。实验表明,该方法在室内环境下能够实时地识别表情并具有较高的识别成功率。

A facial expression recognition system is developed based on the robot vision to meet the facial expression recognition requirement of service robot＇s vision-based human-robot communication. Firstly, the face region is localized based on skin color and Gabor texture, than facial expression features are extracted according to Gabor wavelets transform and the expression classifier is designed based on SVM, 7 basic facial expressions are recognized at last. Results show that facial expressions can be real-timely classified with high success rate under indoor environment by this method.