Facial expression recognition using local binary covariance matrices

摘要：

In this paper, we propose a novel local feature descriptor for facial expression recognition, referred as local binary covariance matrices (LBCM). The covariance matrix in LBCM is constructed by incorporating location, intensity and local binary features of each pixel inside a region of interest. Extensive experiments demonstrate the effectiveness of LBCM for FER, even if partial occlusion exists.

关键词： facial expression recognition local binary pattern region covariance matrix local binary covariance matrix

作者: Song Guo Qiuqi Ruan

作者单位: Institute of Information Science, Beijing Jiaotong University, Beijing 100044, P.R. China

会议类型: 国际会议

会议名称: 2011 the Iet 4th International Conference on Wireless,Mobile & Multimedia Networks(第四届无线、移动及多媒体网络国际会议 ICWMMN2011)

会议地点: 北京

会议语种:英文

页码: 237-242

在线出版日期: 2011-11-27（万方平台首次上网日期，不代表论文的发表时间）