摘要
为了提高人脸识别在复杂条件下的识别率,提出一种基于自适应加权梯度方向直方图特征(AW-HOG)的人脸识别方法。该方法首先将人脸图像分成均匀子块,并利用HOG描述算子提取分块人脸特征,根据各分块对识别的贡献率自适应地计算各分块的权重,然后融合权重系数以及各分块的HOG特征,形成AW-HOG特征并采用主成分分析(PCA)算法进行降维,最后利用支持向量机(SVM)进行分类识别。在Yale B以及AR标准人脸库上的实验结果表明,提出的人脸识别方法在识别率上优于传统算法且对光照具有较强的鲁棒性。
This paper proposes a novel approach for face recognition based on Adaptively Weighted Histograms of OrientedGradients(AW-HOG)to solve the issues of low face recognition rate in complex environments.Firstly,AW-HOG featureis available by fusing the weighting map and the traditional HOG feature of the sub-images divided from the originalwhole face images.And the weighting map is adaptively computed on account of the contribution of each sub-image.After that,the dimensions of AW-HOG features are reduced by Principal Component Analysis(PCA)and the final classificationfeatures are generated.Finally,Support Vector Machine(SVM)is utilized in face classification and recognitionusing the final features.Experimental results based on Yale B and AR standard face databases demonstrate that theproposed approach not only obviously enhances face recognition rate in complex environments but also has certain robustnessto the influence of light and expression.
作者
胡丽乔
仇润鹤
HU Liqiao;QIU Runhe(College of Information Sciences and Technology, Donghua University, Shanghai 201620, China;Engineering Research Center of Digitized Textile & Fashion Technology, Donghua University, Shanghai 201620, China)
出处
《计算机工程与应用》
CSCD
北大核心
2017年第3期164-168,共5页
Computer Engineering and Applications
基金
上海市教委科研创新重点项目(No.12ZZ059)
关键词
人脸识别
梯度方向直方图
主成分分析
自适应加权
支持向量机
face recognition
Histograms of Oriented Gradients(HOG)
Principal Component Analysis(PCA)
adaptively weighted
Support Vector Machine(SVM)
