基于Gabor参数矩阵与改进Adaboost的人脸表情识别  

Facial expression recognition based on Gabor parameters matrix and improved Adaboost

作　　者：杨凡[1] 张磊[1] 

机构地区：[1]兰州工业学院软件工程学院,兰州730050

出　　处：《计算机应用》2014年第4期1134-1138,共5页journal of Computer Applications

基　　金：兰州工业学院青年科技创新基金资助项目(13K-009)

摘　　要：针对目前人脸表情识别(FER)中Gabor特征维数高、计算量大并且存在特征冗余的问题,提出一种基于Gabor参数矩阵与改进Adaboost的人脸表情识别算法。首先,结合图像像素信息与Gabor小波核的参数定义Gabor参数矩阵;其次,在Adaboost中引入遗传算法(GA)的思想改进其搜索性能,并利用改进的Adaboost选择与Gabor参数矩阵元素对应的最优特征来构建强分类器,从而通过特征选择的方法降低Gabor特征的维数和冗余,减少计算量;最后,在构建多个强分类器的基础上,提出多表情分类算法实现面部表情的分类识别。基于Matlab的实验结果表明,该算法的平均表情识别率为89.67%,且最优特征的选取效率得到明显提高。To solve the problems of high-dimensionality,giant-computation and redundancy of Gabor features in current Facial Expression Recognition （FER）,a new FER algorithm based on Gabor Parameter Matrix （GPM） and improved Adaboost was proposed.Firstly,the GPM was defined by combining pixel information of image and parameters of Gabor wavelet kernel;Secondly,the idea of Genetic Algorithm （GA） was introduced into Adaboost to improve its searching porformance,then the improved Adaboost was used to select optimal features corresponding to the elements in GPM to build strong classifiers,thereby the dimensionalities,redundancy and calculation amount of Gabor features could be reduced by feature selection;Finally,on the basis of building several strong classifiers,a multi-expressions classification algorithm was developed to implement FER.The experimental results on Maflab indicate that average expression recognition rote of the proposed algorithm is 89.67％,and the selection efficiency of optimal features is improved significantly.

关 键 词：人脸表情识别 GABOR特征 GABOR小波 遗传算法 ADABOOST 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]