基于梯度Gabor直方图特征的表情识别方法  

Expression Recognition Method Based on Gradient Gabor Histogram Features

作　　者：胡敏[1] 朱弘[1] 王晓华[1] 许良凤[1] 

机构地区：[1]合肥工业大学计算机与信息学院情感计算与先进智能机器安徽省重点实验室,合肥230009

出　　处：《计算机辅助设计与图形学学报》2013年第12期1856-1861,共6页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家"八六三"高技术研究发展计划(2012AA011103);国家自然科学基金-广东联合基金重点项目(U1135003);情感计算与先进智能机器安徽省重点实验室;安徽省科技计划项目(1206c0805039)

摘　　要：针对传统Gabor特征在表情识别上的局限性,提出一种基于梯度Gabor直方图(GGH)特征的表情识别方法.首先对预处理后的人脸图像进行Gabor特征提取;然后将相同尺度、不同方向的Gabor特征按照梯度方向构造Gabor特征融合图,再对融合图进行分块并计算每个子块的直方图分布,从而构成人脸的GGH特征;最后采用支持向量机对GGH特征进行人脸表情分类.在JAFFE库与Pain Expressions库上进行交叉验证的结果表明,在保证较高识别率时,GGH特征比传统的Gabor特征实时性更高.In order to overcome the limitation of traditional Gabor features in expression recognition, an expression recognition method based on gradient Gabor histogram （GGH） features is proposed. Firstly the fusion rule of gradient direction is used for fusing the original Oabor features on the same scale and different directions after pretreatment. Then GGH features are extracted from block histogram features of Gabor feature fusion diagram. Finally, facial expression classification are achieved by using support vector machine. Experimental results in JAFFE database and Pain Expressions database show that GGH features are more real-time than the traditional Gabor features when the higher recognition rate is ensured.

关 键 词：GABOR特征 表情识别 梯度Gabor直方图 分块直方图 梯度方向 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]