摘要
针对人脸识别中光照、表情、姿态的影响,提出一种融合双向二维线性鉴别分析和局部对称平均的人脸识别新方法。通过双向二维线性鉴别分析对整幅图像进行特征提取,利用局部奇异值分解对称平均提取图像的局部特征。对2种方法提取到的特征利用基于加权欧式距离的最近邻分类器进行融合识别,在ORL人脸库上的实验结果证明了该方法的有效性。
A novel method based on Bilateral Two-Dimensional Linear Discriminant Analysis(B-2DLDA) and symmetry average of local Singular Value Decomposition(SVD) for face recognition is presented. B-2DLDA is used to extract features on the whole face image. Symmetry average of local SVD is used to extract the local facial features. By fusing the extracted features from both two methods above, the nearest neighbor classifier based on the weighted-Euclidean distance is employed to accomplish the task of classification. Experimental results carried on ORL face database validate the efficiency of the method.
出处
《计算机工程》
CAS
CSCD
北大核心
2009年第17期181-183,186,共4页
Computer Engineering
基金
国家自然科学基金资助项目(60673190)
江苏大学高级专业人才科研启动基金资助项目(05JDG020)
关键词
双向二维线性鉴别分析
局部奇异值分解
特征融合
加权欧氏距离
人脸识别
Bilateral Two-Dimensional Linear Discriminant Analysis(B-2DLDA)
local Singular Value Decomposition(SVD)
fusion of features
weighted-Euclidean distance
face recognition