[1]高纪东,王正群,夏 进.基于 HOG 特征的加权稀疏表示人脸识别算法[J].计算机技术与发展,2022,32(07):64-69.[doi:10. 3969 / j. issn. 1673-629X. 2022. 07. 011]
　GAO Ji-dong,WANG Zheng-qun,XIA Jin.Weighted Sparse Representation Face Recognition Algorithm Based on HOG Feature[J].,2022,32(07):64-69.[doi:10. 3969 / j. issn. 1673-629X. 2022. 07. 011]
点击复制

基于 HOG 特征的加权稀疏表示人脸识别算法()

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

卷:
32
期数:
2022年07期
页码:
64-69
栏目:
图形与图像
出版日期:
2022-07-10

文章信息/Info

Title:
Weighted Sparse Representation Face Recognition Algorithm Based on HOG Feature
文章编号:
1673-629X(2022)07-0064-06
作者:
高纪东; 王正群; 夏 进
扬州大学 信息工程学院,江苏 扬州 225127
Author(s):
GAO Ji-dong; WANG Zheng-qun; XIA Jin
School of Information Engineering,Yangzhou University,Yangzhou 225127,China
关键词:
人脸识别; 随机投影; 稀疏系数; 方向梯度直方图; 加权稀疏表示
Keywords:
face recognition; random projection; sparse coefficient; HOG feature; weighted sparse representation
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 07. 011
摘要:
在人脸识别中,为了进一步提高人脸图像对光照等外界因素的鲁棒性,提出一种基于 HOG 特征的加权稀疏表示算法, 将加权 稀疏表示方法和 HOG 特征以及随机投影方法相融合,以降低复杂度,提高识别性能。 首先,统计每一幅图像的方向梯度直方 图( HOG) 特征,并对每一幅图像进行归一化处理,削弱人脸图像中的光照影响;其次,对归一化后的图像引入随机矩阵算法,进 行多次随机投影,得到每个样本所对应的稀疏系数,利用样本之间的距离作为稀疏系数的权值;在此基础上,对传统稀疏表示分类器进行改进,样本经随机矩阵多次投影和稀疏表示后会产生多个重构残差,最后利用样本的重构残差和对样本进行识别分类。 ORL 人脸库和 GT 人脸数据库上的实验证明该方法对光照等外界物理因素有着很好的鲁棒性。
Abstract:
In face recognition,in order to further improve the robustness of face image to external factors such as illumination,a weighted sparse representation algorithm based on hog feature is proposed. The weighted sparse representation method is combined with HOG feature and random projection method to reduce complexity and improve recognition performance. Firstly, the HOG features of each image are counted,and each image is normalized to weaken the influence of illumination in the face image. Secondly,the random matrix algorithm is introduced into the normalized image,and the sparse coefficient corresponding to each sample is obtained by multiple random projections. The distance between samples is used as the weight of the sparse coefficient. On this basis, the traditional sparse representation classifier is improved. After multiple projections of random matrix and sparse representation, multiple reconstruction residuals will be generated. Finally,the reconstruction residuals of samples are used to identify and classify samples. Experiments on ORL face database and GT face database show that the proposed method is robust to external physical factors such as illumination.

相似文献/References:

[1]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].,2010,(07):51.
[2]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].,2009,(07):84.
[3]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].,2008,(07):161.
[4]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].,2008,(07):227.
[5]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].,2008,(07):46.
[6]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].,2007,(07):144.
[7]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].,2007,(07):63.
[8]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].,2007,(07):118.
[9]马驰 阮秋琦.基于离散微粒群优化算法的SVM参数选择[J].计算机技术与发展,2007,(12):20.
　MA Chi,RUAN Qiu-qi.Parameter Selection for SVM Based on Discrete PSO[J].,2007,(07):20.
[10]孔敏 陈思宝 罗斌.基于图谱分解的人脸表情分析[J].计算机技术与发展,2006,(04):33.
　KONG Min,CHEN Si-bao,LUO Bin.Facial Expression Analysis Based on Graph Spectral Decomposition[J].,2006,(07):33.

更新日期/Last Update: 2022-07-10