基于特征融合的人脸图像识别方法研究  

Study of face recognition method based on feature fusion

作　　者：梅蓉[1] 

机构地区：[1]南京森林警察学院侦查系,江苏南京210023

出　　处：《河南科技学院学报（自然科学版）》2014年第4期70-74,共5页Journal of Henan Institute of Science and Technology(Natural Science Edition)

基　　金：中央高校基本科研业务费专项资金资助项目(LGZD201325)

摘　　要：为了提高人脸识别率,研究了一种基于边缘二值图像特征向量提取的方法.通过局部二值模式提取特征向量,考虑到边缘二值图像特征向量与局部二值模式提取的特征向量的区别,提出了将这两类特征向量通过PCA方法融合实现人脸识别的方法.实验结果表明基于两类特征向量融合的人脸识别方法可以有效地提高识别率.To improve the face recognition rate,a feature vector extraction method has been studied based on edge binary image.The feature vector has been extracted by local binary model and the method of face recognition by fusion of PCA for the two kinds of feature vectors has been proposed taking into account the difference between edge binary feature vector and partial binary feature vector.The experimental results showed that the face recognition method based on the fusion of two kinds of feature vectors can effectively improve the recognition rate.

关 键 词：人脸识别 边缘特征向量 局部二值模式 主成分分析 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]