[1]韩 肖,马 祥.基于二进制标签松弛模型的遮挡人脸识别[J].计算机技术与发展,2022,32(01):1-6.[doi:10. 3969 / j. issn. 1673-629X. 2022. 01. 001]
　HAN Xiao,MA Xiang.Occlusion Face Recognition Based on Binary Label Relaxation[J].,2022,32(01):1-6.[doi:10. 3969 / j. issn. 1673-629X. 2022. 01. 001]
点击复制

基于二进制标签松弛模型的遮挡人脸识别()
分享到：

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

卷:
32
期数:
2022年01期
页码:
1-6
栏目:
人工智能
出版日期:
2022-01-10

文章信息/Info

Title:
Occlusion Face Recognition Based on Binary Label Relaxation
文章编号:
1673-629X(2022)01-0001-06
作者:
韩 肖; 马 祥
长安大学 信息工程学院,陕西 西安 710064
Author(s):
HAN Xiao; MA Xiang
School of Information Engineering,Chang爷 an University,Xi爷 an 710064,China
关键词:
人脸识别; 低秩技术; 二进制松弛标签; 特征提取; 遮挡
Keywords:
face recognition; low rank technology; binary relaxation label; feature extraction; occlusion
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 01. 001
摘要:
遮挡人脸识别是人脸识别系统面临的挑战之一。 在自然场景下,人脸特征通常被口罩等物品遮挡,导致人脸特征不完整,从而无法正确提取人脸特征信息,严重影响最终的识别结果。 针对有遮挡条件下人脸识别效果较差的问题,通过利用低秩技术和二进制标签松弛模型的优势,该文提出了一种新的基于二进制松弛标签的回归模型。 该模型通过学习一个更松弛的标签矩阵来代替严格的 0-1 标签矩阵,从而扩大了样本之间的类间距离,同时对二进制松弛标签矩阵采用低秩约束,以提高样本的类内相似性。 因此,该方法能够提取出更多具有判别性的特征,从而有利于遮挡条件下的人脸识别。 此外,通过引入的正则化项,有效避免了该方法的过拟合问题。 在 Yale B、LFW 和 CMU PIE 数据集上的实验结果表明,该方法不仅能在实验室环境下获得较高的识别率,在自然场景下仍然能取得较好的识别性能。
Abstract:
Occlusion face recognition is one of the challenges faced by face recognition systems. In natural scenes, face features areusually occluded by masks and other items,resulting in incomplete face features,which cannot correctly extract facial feature informationand seriously affect the final recognition results. Aiming at the problem of poor face recognition under occlusion, we propose a newregression model based on binary label relaxation by using the advantages of low-rank technology and binary label relaxation model. Themodel expands the inter-class distance between samples by learning a more relaxed label matrix instead of the strict 0-1 label matrix,anduses low-rank constraints on the binary relaxed label matrix to improve the intra-class similarity of the samples. Therefore,the proposedmethod can extract more discriminative features,which is beneficial to face recognition under occlusion. In addition, the introduced regu鄄larization term effectively avoids the over-fitting problem of the proposed method. The experimental results on the Yale B,LFW andCMU PIE datasets show that the proposed method can not only obtain a higher recognition rate in the laboratory environment,but alsoachieve better recognition performance in the natural scene.

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].,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].,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].,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].,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].,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].,2008,(01):46.
[7]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,(01):144.
[8]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,(01):63.
[9]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,(01):118.
[10]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,(01):20.

更新日期/Last Update: 2022-01-10