基于自动分割的局部Gabor小波人脸表情识别算法  

Facial expression recognition algorithm based on local Gabor wavelet automatic segmentation

作　　者：刘姗姗[1,2] 王玲[1,2] 

机构地区：[1]四川师范大学计算机科学学院,成都610101 [2]四川省可视化计算与虚拟现实重点实验室,成都610101

出　　处：《计算机应用》2009年第11期3040-3043,共4页journal of Computer Applications

基　　金：国家自然科学基金资助项目(608731021F020508)

摘　　要：针对包含表情信息的静态灰度图像,提出基于自动分割的局部Gabor小波人脸表情识别算法。首先使用数学形态学与积分投影相结合定位眉毛眼睛区域,采用模板内计算均值定位嘴巴区域,自动分割出表情子区域。接着,对分割出的表情子区域进行Gabor小波变换提取表情特征,再利用Fisher线性判别分析进行选择,有效地去除了表情特征的冗余性和相关性。最后利用支持向量机实现对人脸表情的分类。用该算法在日本女性表情数据库上进行测试,实现了自动化且易于实现,结果证明了该方法的有效性。A local Gabor wavelet facial expression recognition algorithm based on automatic segmentation to the still image containing facial expression information was introduced. Firstly, mathematical morphology combined with projection was used to locate the brow and eye region, and the mouth region was located by calculating template average, which can segment the expression sub-regions automatically. Secondly, features of the expression sub-regions were extracted by Gabor wavelet transformation and then effective Gabor expression features were selected by Fisher Linear Discriminant （FLD） analysis, removing the redundancy and relevance of expression features. Finally the features were sent to Support Vector Machine （SVM） to classify different expressions. The algorithm was tested on Japanese female facial expression database. It is easy to realize automation. The feasibility of this method has been verified by experiments.

关 键 词：GABOR小波变换 表情特征提取 FISHER线性判别分析 支持向量机 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]