摘要
提出了一种基于Gabor小波变换的人脸表情特征提取算法。针对包含表情信息的静态灰度图像,首先对其预处理,然后对表情子区域执行Gabor小波变换,提取表情特征矢量,进而构建表情弹性图。最后分析比较了在不同光照条件下不同测试者做出6种基本表情时所提取的表情特征,结果表明Gabor小波变换能够有效地提取与表情变化有关的特征,并能有效地屏蔽光照变化及个人特征差异的影响。
This paper introduces a facial expression features extraction algorithm. Given a still image containing facial expression information,preprocessors are executed firstly. Secondly, expression feature vectors of the expression sub-regions are extracted by Gabor wavelet transformation to form expression elastic graph. Different expression features are extracted and compared while different subjects display six basic expressions with illumination variety. Experiment shows that expression features can be extracted effectively based on Gabor wavelet transformation, which is insensitive to illumination variety and individual difference.
出处
《计算机工程》
EI
CAS
CSCD
北大核心
2005年第15期172-174,共3页
Computer Engineering
基金
国家自然科学基金资助项目(60273040)
江苏省高校自然科学基金资助项目(02KJB520003)
关键词
模式识别
表情特征提取
GABOR小波变换
Pattern recognition
Expression feature extraction
Gabor wavelet transformation
