[1]马园园,张登银.基于 SVD 的两步人脸识别方法[J].计算机技术与发展,2018,28(01):95-99.[doi:10.3969/ j. issn.1673-629X.2018.01.020]
　MA Yuan-yuan,ZHANG Deng-yin.A Two-step Face Recognition Method Based on SVD[J].Computer Technology and Development,2018,28(01):95-99.[doi:10.3969/ j. issn.1673-629X.2018.01.020]
点击复制

基于 SVD 的两步人脸识别方法
()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
28
期数:
2018年01期
页码:
95-99
栏目:
智能、算法、系统工程
出版日期:
2018-01-10

文章信息/Info

Title:
A Two-step Face Recognition Method Based on SVD
文章编号:
1673-629X(2018)01-0095-05
作者:
马园园; 张登银
南京邮电大学 通信与信息工程学院,江苏 南京 210003
Author(s):
MA Yuan-yuan; ZHANG Deng-yin
School of Communications and Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210003,China
关键词:
奇异值分解; 人脸识别; 奇异值向量; 矩阵相似度; 两步识别; 特征提取
Keywords:
singular value decomposition; face recognition; singular value vector; matrix similarity; two-step recognition; feature extraction
分类号:
TP391.41
DOI:
10.3969/ j. issn.1673-629X.2018.01.020
文献标志码:
A
摘要:
常规方法使用奇异值分解进行人脸识别时,多以奇异值向量作为区分特征,没有充分利用奇异值分解获得的有效信息,识别效果并不理想。 为了进一步提高识别精度,提出一种基于奇异值向量识别与矩阵相似度判别相结合的两步人脸识别方法。第一步,将图像划分成块,求得图像整体和局部分块的奇异值向量,把整体与局部的奇异值向量按照一定顺序组合后作为识别特征进行人脸的初步识别,获得候选人脸集;第二步,求候选人脸与待测人脸整体正交矩阵的相似程度,以此为识别特征进一步精确识别获得最佳决策脸。为了验证该方法的有效性,利用ORL 人脸数据库进行了两组分析对比实验。 实验结果表明,该方法在识别率上明显优于常规方法,且无需使用太多训练样本就能达到很理想的识别精度,具有很大的实用价值。
Abstract:
When singular value decomposition is used in face recognition,singular value vector is usually used as the recognition feature,and the effective information obtained by singular value decomposition is not fully utilized,which leads to an unsatisfactory recognition effect. To further improve the accuracy of face recognition,a new two step face recognition method based on the singular value vector identification and orthogonal matrix similarity judgment is proposed. First,the singular value vector from both the whole image and the partial block is obtained after dividing the image into blocks;the global and local singular value vectors are combined as a recognition feature to obtain the candidate set in the initial recognition. Then,the similarity degree of the whole orthogonal matrix between the candidate face and the face to be measured is obtained,which is used as the recognition feature to further identify the best decision face. To prove the validity of the proposed method,two sets of experiments are conducted using ORL face database. Experiment shows that it is superior to the conventional method in recognition rate,and can achieve high recognition rate without using too many training samples,so it has great practical value.

相似文献/References:

[1]徐钊,吴光敏,覃世欢.基于AccelDSP的LBP算法在人脸识别中的应用[J].计算机技术与发展,2014,24(01):51.
　XU Zhao,WU Guang-min,QIN Shi-huan.Application of LBP Algorithm Based on AccelDSP in Face Recognition[J].Computer Technology and Development,2014,24(01):51.
[2]时书剑 马燕.基于Gabor滤波和KPCA的人脸识别方法[J].计算机技术与发展,2010,(04):51.
　SHI Shu-jian,MA Yan.Face Recognition Based on Gabor Filters and Kernel Principal Component Analysis[J].Computer Technology and Development,2010,(01):51.
[3]袁健 姚明海.基于简化局部二元法的人脸特征提取[J].计算机技术与发展,2009,(06):84.
　YUAN Jian,YAO Ming-hai.Facial Feature Extraction Based on Simplified Local Binary Patterns[J].Computer Technology and Development,2009,(01):84.
[4]李伟.人脸识别算法在智能手机上的实现[J].计算机技术与发展,2008,(01):161.
　LI Wei.Implementation of Face Identification in Intelligent Mobile Telephone[J].Computer Technology and Development,2008,(01):161.
[5]黄国宏 刘刚.一种新的基于Fisher准则的线性特征提取方法[J].计算机技术与发展,2008,(05):227.
　HUANG Guo-hong,LIU Gang.A New Linear Feature Extraction Method Based on Fisher Criterion[J].Computer Technology and Development,2008,(01):227.
[6]孙晓玲 侯德文 储凡静.人脸识别中的眼睛定位方法[J].计算机技术与发展,2008,(10):46.
　SUN Xiao-ling,HOU De-wen,CHU Fan-jing.Eye Location in Face Recogniton[J].Computer Technology and Development,2008,(01):46.
[7]赵振勇 王保华 王力 崔磊.人脸图像的特征提取[J].计算机技术与发展,2007,(05):221.
　ZHAO Zhen-yong,WANG Bao-hua,WANG Li,et al.The Feature Extraction of Face Images[J].Computer Technology and Development,2007,(01):221.
[8]王静 谭同德.基于梯度和模板二次匹配的人眼定位[J].计算机技术与发展,2007,(10):144.
　WANG Jing,TAN Tong-de.A Method to Eyes Location Based on Step- Direction and Templet - Matching[J].Computer Technology and Development,2007,(01):144.
[9]高宏娟 潘晨.基于非负矩阵分解的人脸识别算法的改进[J].计算机技术与发展,2007,(11):63.
　GAO Hong-juan,PAN Chen.Improved Face Recognition Algorithm Based on Non- Negative Matrix Factorization[J].Computer Technology and Development,2007,(01):63.
[10]徐勇 张海 周森鑫 王辉.基于统计学习理论的人脸识别方法研究[J].计算机技术与发展,2007,(11):118.
　XU Yong,ZHANG Hai,ZHOU Sen-xin,et al.Research on Face Recognition Based on Statistical Learning Theory[J].Computer Technology and Development,2007,(01):118.

更新日期/Last Update: 2018-03-13