摘要
针对人脸图像特征提取,应用主成分分析和二维主成分分析方法,提出用二维特征求解样本的隶属度,用主成分特征进行支持向量机分类的方法。该方法结合了二维主成分特征在选取少量分量时人脸重构图像稳定的优点和主成分特征重构图像局部特征清晰的优点。为了与二维主成分特征分类结果进行比较,通过引入矩阵内积,给出了针对二维特征的三类核函数。实验表明利用两种特征进行分类的方法在人脸识别中具有较高的精度。
According to analyze the main component analysis and the two-dimensional principal component analysis regarding face image feature extraction,using two-dimensional features for the calculation of the membership,this paper proposed the principal component for support vector classification.The method combined the stabilization of two-dimensional principal component in reconstructing face image and the obviousness of the principal component to the reconstructed image local characteristics.In order to contrast with the sort results of two-dimensional characteristics,through introduction of matrix inner product,gave three types of two-dimensional characteristics kernel function.Experiments show that the method has a high classification accuracy for face recognition.
出处
《计算机应用研究》
CSCD
北大核心
2011年第7期2789-2792,共4页
Application Research of Computers
基金
湖南省科技厅计划资助项目(2010CK3023
2009JT3003)
湖南省大学生研究性学习和创新性实验计划基金资助项目
长沙理工大学教研教改课题(JG1030
CN1006)
关键词
模糊支持向量机
隶属度
主成分分析
二维主成分分析
人脸识别
fuzzy support vector machine
membership
principle component analysis
two-dimensional principal component analysis
face recognition
