正在加载图片...
第14卷第2期 智能系统学报 Vol.14 No.2 2019年3月 CAAI Transactions on Intelligent Systems Mar.2019 D0:10.11992/tis.201708015 网络出版地址:http:/kns.cnki.net/kcms/detail/23.1538.TP.20180420.1125.008.html 基于正交Log-Gabor滤波二值模式的人脸识别算法 杨恢先,付宇,曾金芳,徐唱 (湘潭大学物理与光电工程学院,湖南湘潭411105) 摘要:为消除可变光照对人脸识别的影响,提出一种基于正交Log-Gabor滤波二值模式(OLGBP)的人脸识别 算法。该算法对样本在正交方向做Log-Gabor变换,然后将所得特征图像进行虚实分解和同尺度多方向二值融 合构成OLGBP特征向量,再将这些特征向量构成协同表征字典D。最后,在字典D下对测试样本采用协同表 征求稀疏系数,并通过误差重构来分类。在AR、Extend Yale B和CAS-PEAL-Rl人脸数据库上的实验结果表 明,OLGBP算法对光照变化的单样本人脸识别具有较好的效果,从而验证了算法的有效性。 关键词:人脸识别;Log-Gabor滤波器;协同表征;正交:稀疏编码;二值模式;单样本;多尺度 中图分类号:TP391.4文献标志码:A 文章编号:1673-4785(2019)02-0330-08 中文引用格式:杨恢先,付宇,曾金芳,等.基于正交Log-Gabor滤波二值模式的人脸识别算法.智能系统学报,2019, 14(2):330-337. 英文引用格式:YANG Huixian,,FUYu,ZENG Jinfang,etal.Face recognition based on orthogonal Log-Gabor binary pattern[J. CAAI transactions on intelligent systems,2019,14(2):330-337. Face recognition based on orthogonal Log-Gabor binary pattern YANG Huixian,FU Yu,ZENG Jinfang,XU Chang (School of Physics and Optoelectronic,Xiangtan University,Xiangtan 411105,China) Abstract:To eliminate the effect of varying illumination on face recognition,a novel method of face recognition based on orthogonal log-Gabor binary pattern(OLGBP)is proposed in this paper.First,the algorithm performs log-Gabor transform on the samples in the orthogonal direction.Then the log-Gabor feature image is decomposed into real and imaginary parts,and the OLGBP feature vectors are constructed by fusing them into a binary pattern in the same scale at different directions.These feature vectors then form a collaboratively representative dictionary D.Finally,sparse coeffi- cients are obtained by collaboratively representing these feature vectors with the test samples based on the dictionary D. and the test samples are classified by reconstruction of errors.The results for experiments performed on AR,Extend Yale B,and CAS-PEAL-RI face databases show that the OLGBP algorithm has good effect on a single sample with il- lumination variation,and the effectiveness of the algorithm is verified. Keywords:face recognition;Log-Gabor filter,collaborative representation;orthogonality;sparse coding;binary pattern; single sample;multi scale 人脸识别因其友好性、无侵害、易获取等特 经典的人脸识别算法有Eigenface)、Fisher-. 点,成为图像处理和计算机视觉中受关注的领域 face、拉普拉斯脸等。2009年,John Wright等 之一。提取区分性好、鲁棒性好的人脸特征,构 提出一种基于稀疏表示分类(sparse representation 建高效可靠的分类器,来提升人脸识别的正确 based classification,SRC)人脸识别算法。SRC算 率,一直是人脸识别研究的难点与重点"。 法首先在训练图像上对未知图像做编码处理,然 收稿日期:2017-08-17.网络出版日期:2018-04-20 后通过计算最小编码误差来估计未知图像属于哪 基金项目:湘潭大学博士启动基金项目(KZ07089):湘潭大学校 级科研项目(16XZX02). 一类,从而达到分类目的。SRC的快捷与高效 通信作者:付字.E-mail:22682322@qq.com 性,使得它广泛用于人脸识别领域。SRC过度强DOI: 10.11992/tis.201708015 网络出版地址: http://kns.cnki.net/kcms/detail/23.1538.TP.20180420.1125.008.html 基于正交 Log-Gabor 滤波二值模式的人脸识别算法 杨恢先,付宇,曾金芳,徐唱 (湘潭大学 物理与光电工程学院,湖南 湘潭 411105) 摘 要:为消除可变光照对人脸识别的影响,提出一种基于正交 Log-Gabor 滤波二值模式 (OLGBP) 的人脸识别 算法。该算法对样本在正交方向做 Log-Gabor 变换,然后将所得特征图像进行虚实分解和同尺度多方向二值融 合构成 OLGBP 特征向量,再将这些特征向量构成协同表征字典 D。最后,在字典 D 下对测试样本采用协同表 征求稀疏系数,并通过误差重构来分类。在 AR、Extend Yale B 和 CAS-PEAL-R1 人脸数据库上的实验结果表 明,OLGBP 算法对光照变化的单样本人脸识别具有较好的效果,从而验证了算法的有效性。 关键词:人脸识别;Log-Gabor 滤波器;协同表征;正交;稀疏编码;二值模式;单样本;多尺度 中图分类号:TP391.4 文献标志码:A 文章编号:1673−4785(2019)02−0330−08 中文引用格式:杨恢先, 付宇, 曾金芳, 等. 基于正交 Log-Gabor 滤波二值模式的人脸识别算法[J]. 智能系统学报, 2019, 14(2): 330–337. 英文引用格式:YANG Huixian, FU Yu, ZENG Jinfang, et al. Face recognition based on orthogonal Log-Gabor binary pattern[J]. CAAI transactions on intelligent systems, 2019, 14(2): 330–337. Face recognition based on orthogonal Log-Gabor binary pattern YANG Huixian,FU Yu,ZENG Jinfang,XU Chang (School of Physics and Optoelectronic, Xiangtan University, Xiangtan 411105, China) Abstract: To eliminate the effect of varying illumination on face recognition, a novel method of face recognition based on orthogonal log-Gabor binary pattern (OLGBP) is proposed in this paper. First, the algorithm performs log-Gabor transform on the samples in the orthogonal direction. Then the log-Gabor feature image is decomposed into real and imaginary parts, and the OLGBP feature vectors are constructed by fusing them into a binary pattern in the same scale at different directions. These feature vectors then form a collaboratively representative dictionary D. Finally, sparse coeffi￾cients are obtained by collaboratively representing these feature vectors with the test samples based on the dictionary D, and the test samples are classified by reconstruction of errors. The results for experiments performed on AR, Extend Yale B, and CAS-PEAL-R1 face databases show that the OLGBP algorithm has good effect on a single sample with il￾lumination variation, and the effectiveness of the algorithm is verified. Keywords: face recognition; Log-Gabor filter; collaborative representation; orthogonality; sparse coding; binary pattern; single sample; multi scale 人脸识别因其友好性、无侵害、易获取等特 点,成为图像处理和计算机视觉中受关注的领域 之一。提取区分性好、鲁棒性好的人脸特征,构 建高效可靠的分类器,来提升人脸识别的正确 率,一直是人脸识别研究的难点与重点[1]。 经典的人脸识别算法有 Eigenface[2] 、Fisher￾face[3] 、拉普拉斯脸[4]等。2009 年,John Wright 等 [5] 提出一种基于稀疏表示分类 (sparse representation based classification,SRC) 人脸识别算法。SRC 算 法首先在训练图像上对未知图像做编码处理,然 后通过计算最小编码误差来估计未知图像属于哪 一类,从而达到分类目的。SRC 的快捷与高效 性,使得它广泛用于人脸识别领域。SRC 过度强 收稿日期:2017−08−17. 网络出版日期:2018−04−20. 基金项目:湘潭大学博士启动基金项目 (KZ07089);湘潭大学校 级科研项目 (16XZX02). 通信作者:付宇. E-mail: 292682322@qq.com. 第 14 卷第 2 期 智 能 系 统 学 报 Vol.14 No.2 2019 年 3 月 CAAI Transactions on Intelligent Systems Mar. 2019
向下翻页>>
©2008-现在 cucdc.com 高等教育资讯网 版权所有