基于低秩矩阵恢复和Gabor特征的遮挡人脸识别

孙雨浩; 陶洋; 胡昊

Chinese

您当前的位置：

首页 >

文章列表页 >

基于低秩矩阵恢复和Gabor特征的遮挡人脸识别

更新时间：2026-09-04

- 基于低秩矩阵恢复和Gabor特征的遮挡人脸识别
- Occlusion face recognition based on low-rank matrix recovery and Gabor feature
- 微电子学与计算机 2020年37卷第3期页码：42-48
- 作者机构：
  
  重庆邮电大学机构通信与信息工程学院,重庆,400065
- 作者简介：
- 基金信息：
- DOI：
  中图分类号：
- 纸质出版：2020
- 稿件说明：
移动端阅览
孙雨浩, 陶洋, 胡昊. 基于低秩矩阵恢复和Gabor特征的遮挡人脸识别[J]. 微电子学与计算机, 2020, 37(3): 42-48.

SUN Yu-hao, TAO Yang, HU Hao. Occlusion face recognition based on low-rank matrix recovery and Gabor feature[J]. 2020, 37(3): 42-48.
孙雨浩, 陶洋, 胡昊. 基于低秩矩阵恢复和Gabor特征的遮挡人脸识别[J]. 微电子学与计算机, 2020, 37(3): 42-48. DOI：

SUN Yu-hao, TAO Yang, HU Hao. Occlusion face recognition based on low-rank matrix recovery and Gabor feature[J]. 2020, 37(3): 42-48. DOI：

摘要

针对低秩矩阵恢复算法复杂度过高和训练集样本存在遮挡的问题，本文提出一种基于低秩矩阵恢复和Gabor特征的鲁棒表示与分类的遮挡人脸识别方法.该方法首先通过快速低秩矩阵恢复算法，准确并且快速地求得训练样本图像对应的误差图像；然后，分别对“干净”人脸图像和遮挡误差图像进行Gabor变换，得到Gabor特征向量；接着，本文提出一种基于Gabor特征的遮挡字典压缩算法，可以计算出压缩后的Gabor遮挡字典，并用其与训练样本的Gabor特征向量构成Gabor压缩字典；最后，利用压缩字典对测试样本进行协作表示，获取最终的识别结果.在Extended Yale B和AR数据库上的实验结果表明，本方法不仅对遮挡人脸识别具有较强的鲁棒性，而且大大降低了对遮挡人脸图像编码的计算量，缩减了算法的运行时间.

Abstract

To solve the problem of low complexity of low-rank matrix recovery algorithm and occlusion of training set samples

this paper proposes an occlusion face recognition method based on low-rank matrix recovery and Gabor feature robust representation and classification. Firstly

the fast low-rank matrix recovery algorithm is used to accurately and quickly obtain the error image corresponding to the training sample image. Then

Gabor transform is performed on the "clean" face image and the occlusion error image respectively to obtain the Gabor feature vector. Then

In this paper

an occlusion dictionary compression algorithm based on Gabor feature is proposed. The compressed Gabor occlusion dictionary can be calculated and used to form a Gabor compression dictionary with Gabor feature vectors of training samples. Finally

the test samples are cooperatively represented by the compression dictionary. The final recognition result. The experimental results on Extended Yale B and AR database show that the proposed method not only has strong robustness to occlusion face recognition

but also greatly reduces the computational complexity of occlusion face image coding and reduces the running time of the algorithm.

关键词

Keywords

references

LIU G, LIN Z, YAN S, et al. Robust recovery of subspace structures by low-rank representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(1):171-184. DOI: 171

AHARON M, ELAD M, BRUCKSTEIN A M. The K-SVD: an algorithm for designing of overcomplete dictionaries for sparse representation[J]. IEEE Transactions on Signal Processing, 2006, 54(11):4311-4322. DOI: 4311

CANDèS E J, LI X D, MA Y, et al. Robust principal component analysis[J]. Journal of the American Statistical Association, 2009, 8(1):1-73. DOI: 1

YANG M, ZHANG L, SHIU S C K, et al. Gabor feature based robust representation and classification for face recognition with Gabor occlusion dictionary[J]. Pattern Recognition, 2013, 46(7):1865-1878. DOI: 1865

KIM S J, KOH K, LUSTIG M, et al. A method for large-scale l1-regularized least squares[J]. IEEE Journal on Selected Topics in Signal Processing, 2007, 1(4):606-617. DOI: 606

Switzerland COX T L, BOWN J, BELL T R. In advanced l2 reading proficiency assessments, should the question language be in the l1 or the l2?: does it make a difference?[M]. Switzerland: Springer Nature, 2019: 117-136. DOI: 117

HE R, ZHENG W S, HUB G. Maximum correntropy criterion for robust face recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(8): 1561-1676 DOI: 1561

LI X X, DAI D Q, ZHANG X F, et al. Structured sparse error coding for face recognition with occlusion[J]. IEEE Transactions on Image Processing, 2013, 22(5):1889-1900. DOI: 1889

DENG W, HU J, GUO J. Extended SRC: under sampled face recognition via intraclass variant dictionary[J]. IEEE Transactions on Pattern Analysis % Machine Intelligence, 2012, 34(9):1864. DOI: 1864

胡正平, 李静.基于低秩子空间恢复的联合稀疏表示人脸识别算法[J].电子学报, 2013, 41(5): 987-991. DOI: 987

黄淼, 王刘涛, 张海朝.基于Gabor小波变换与K-L高斯黎曼流形判别的人脸识别[J].计算机工程, 2016, 42(9):208-213. DOI: 208

CHENG D, YANG J, WANG J, et al. Double-noise-dual-problem approach to the augmented Lagrange multiplier method for robust principal component analysis[J]. Soft Computing, 2015(21):1-10. DOI: 1

WANG J W, LE N T, LEE J S, et al. Color face image enhancement using adaptive singular value decomposition in fourier domain for face recognition[J]. Pattern Recognition, 2016, 57(C):31-49. DOI: 31

林国军, 解梅.一种鲁棒协作表示的人脸识别算法[J].计算机应用研究, 2014, 31(8): 2520-2522. DOI: 2520

WRIGHT J, YANG A Y, SASTRY S S, et al. Robust face recognition via sparse representation[J]. IEEE Transactions on Pattern Analysis % Machine Intelligence, 2009, 31(2):210-227. DOI: 210

LEI Z, MENG Y, FENG X.Sparse representation or collaborative representation: Which helps face recognition?[C]//International Conference on Computer Vision. Barcelona, Spain, 2011: 471-478

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

AlN/GaN混合缓冲层双异质结p-GaN HEMT直流特性仿真

基于监控指标关联性的微服务异常检测

注意力机制与改进密集卷积引导的信息隐藏模型

一种基于特征上下文理解与切片分析的肺结核检测算法

大模型发展综述：从BERT到Deepseek的技术演进