[1]房梦玉,马明栋.改进的 PCA-LDA 人脸识别算法的研究[J].计算机技术与发展,2021,31(02):65-69.[doi:10. 3969 / j. issn. 1673-629X. 2021. 02. 012]
　FANG Meng-yu,MA Ming-dong.Research on Improved PCA-LDA Face Recognition Algorithm[J].,2021,31(02):65-69.[doi:10. 3969 / j. issn. 1673-629X. 2021. 02. 012]
点击复制

改进的 PCA-LDA 人脸识别算法的研究()
分享到：

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

卷:
31
期数:
2021年02期
页码:
65-69
栏目:
图形与图像
出版日期:
2021-02-10

文章信息/Info

Title:
Research on Improved PCA-LDA Face Recognition Algorithm
文章编号:
1673-629X(2021)02-0065-05
作者:
房梦玉1; 马明栋2
1. 南京邮电大学 通信与信息工程学院,江苏 南京 210003;?
2. 南京邮电大学 地理与生物信息学院,江苏 南京 210003
Author(s):
FANG Meng-yu1; MA Ming-dong2
1. School of Telecommunications & Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210003, China;?
2. School of Geographical and Biological Information,Nanjing University of Posts and Telecommunications,Nanjing 210003,China
关键词:
主成分分析; 线性鉴别分析; 二维主成分分析; Fisher 准则; 人脸识别
Keywords:
principal component analysis; linear discriminant analysis; two-dimensional principal component analysis; Fisher criterion; face recognition
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2021. 02. 012
摘要:
主成分分析算法(PCA)和线性鉴别分析算法(LDA)被广泛用于人脸识别技术中,但是 PCA 由于其计算复杂度高,致使人脸识别的实时性达不到要求。 线性鉴别分析算法存在“小样本”和“边缘类”问题,降低了人脸识别的准确性。 针对上述问题,提出使用二维主成分分析法(2DPCA)与改进的线性鉴别分析法相融合的方法。 二维主成分分析法提取的特征比一维主成分分析法更丰富, 并且降低了计算复杂度。 改进的线性鉴别分析算法重新定义了样本类间离散度矩阵和Fisher 准则,克服了传统线性鉴别分析算法存在的问题,保留了最有辨别力的信息,提高了算法的识别率。 实验结果表明,该算法比主成分分析算法和线性鉴别分析算法具有更高的识别率,可以较好地用于人脸识别任务。
Abstract:
Principal component analysis (PCA) and linear discriminant analysis (LDA)are widely used in face recognition technology. However, the computa-tional complexity of PCA is so high that the real-time performance of face recognition cannot meet the requirements. LDA has“small samples” and “edge” problems, which reduces the accuracy of face recognition. In view of the above problems,we propose a method that fuses two-dimensional principal component analysis and improved linear discriminant analysis. The features extracted by 2DPCA are better, faster than PCA, and the computation time is reduced. The improved LDA redefines the dispersion matrix and Fisher criterion between samples, overcomes the problems of the traditional LDA algorithm, retains the most discerning information,and enhances the recognition rate of the algorithm. The experiment shows that the proposed algorithm has a higher recognition rate than the principal component analysis and linear discriminant analysis, which can be better used for face recognition tasks.

相似文献/References:

[1]夏玫 陈立潮 王新波.一种提高BP神经网络泛化能力的改进算法[J].计算机技术与发展,2009,(09):62.
　XIA Mei,CHEN Li-chao,WANG Xin-bo.A Modified Algorithm to Improve Generalization Ability of BP Neural Network[J].,2009,(02):62.
[2]宋世刚 粘永健 李纲.面向目标检测的高光谱图像压缩技术[J].计算机技术与发展,2009,(11):1.
　SONG Shi-gang,NIAN Yong-jian,LI Gang.Hyperspectral Image Compression Employing Target Detection[J].,2009,(02):1.
[3]俞小娟 胡金柱 李琼 周毕吉.用主成分分析法研究短语字段的判别因素[J].计算机技术与发展,2008,(10):116.
　YU Xiao-juan,HU Jin-zhu,LI Qiong,et al.Studying Factors of Judging Phrase Fields by Method of Principal Component Analysis[J].,2008,(02):116.
[4]刘树利 胡茂林.基于不同视角的人脸模型识别方法[J].计算机技术与发展,2006,(06):213.
　LIU Shu-li,HU Mao-lin.Recognition of Human Face in Different Pose[J].,2006,(02):213.
[5]王辉.主成分分析及支持向量机在人脸识别中的应用[J].计算机技术与发展,2006,(08):24.
　WANG Hui.Application in Human Face Recognition Based on Principal Component Analysis and Support Vector Machine[J].,2006,(02):24.
[6]张靖 葛玮 郝克刚.软件度量中主成分分析方法的研究[J].计算机技术与发展,2006,(12):144.
　ZHANG Jing,GE Wei,HAO Ke-gang.Research of Principal Component Analysis in Software Metrics[J].,2006,(02):144.
[7]职为梅 范明.样本大小对稀有类分类的影响[J].计算机技术与发展,2011,(05):9.
　ZHI Wei-mei,FAN Ming.Impact of Sample Size for Rare-Class Classification[J].,2011,(02):9.
[8]邓炳荣 伍世元 武琳 邵雅雯 李江勇.一种基于计算机嗅觉的卷烟等级识别方法[J].计算机技术与发展,2011,(11):177.
　DENG Bing-rong,WU Shi-yuan,WU Lin,et al.Application of Electronic Nose in Discrimination of Different Levels Cigarette[J].,2011,(02):177.
[9]杨晓斌 周宁宁 杨婷婷.基于统计处理图像放大方法在人脸识别中应用[J].计算机技术与发展,2011,(12):55.
　YANG Xiao-bin,ZHOU Ning-ning,YANG Ting-ting.Application of an Image Magnification Method Based on Statistical Processing in Face Recognition[J].,2011,(02):55.
[10]王建雄 张立民 钟兆根.基于FastICA算法的盲源分离[J].计算机技术与发展,2011,(12):93.
　WANG Jian-xiong,ZHANG Li-min,ZHONG Zhao-gen.Blind Source Separation Based on FastICA Algorithm[J].,2011,(02):93.
[11]张瑞霞 王勇.融合PCA和LDA的入侵检测算法[J].计算机技术与发展,2009,(11):132.
　ZHANG Rui-xia,WANG Yong.Fusion of PCA and LDA for Intrusion Detection[J].,2009,(02):132.

更新日期/Last Update: 2020-02-10