摘要
提出了一种基于分类器联合的人脸表情识别方法。首先采用CKFD算法在双决策子空间中提取两类表情特征并融合;分别利用最近邻、最小距离和神经网络三种子分类器进行识别;最后运用模糊积分对子分类器的识别结果进行融合。基于JAFFE的实验结果表明,它是一种有效的表情识别方法。
A facial expression recognition method based on muhiclassifier fusion with fuzzy integral has been proposed in this paper;First,applied the CKFD to extract two kinds of expression feature in double discriminant subspace and fuse them;Then the Nearest Neighbor（NN）,Minimum Distance（MD） and Radial Basis Function Neural Network（RBFNN） have been used to classify facial expression;Finally,fuzzy integral has been applied to fuse outputs from three classifiers to get the final recognition result. Experimental result on JAFFE show that it is a valid method for facial expression recognition .
出处
《计算机工程与应用》
CSCD
北大核心
2007年第25期244-245,248,共3页
Computer Engineering and Applications
基金
广东省自然科学基金( the Natural Science Foundation of Guangdong Province of China under Grant No.032356) 。
关键词
模糊积分
分类器融合
人脸表情识别
fuzzy integral
multiclassifier fusion
facial expression recognition
