一种融合Gabor+SIFT特征的人脸识别算法

doi:10.16180/j.cnki.issn1007-7820.2019.04.001

摘要/Abstract

摘要：

姿态变化和光照干扰对于人脸识别的准确率和效率有很大影响。针对这一问题,文中采用结合Gabor特征和SIFT特征的人脸识别方法进行识别,提取一幅人脸图像的多个方向和多个尺度的Gabor特征,并将提取得到的Gabor特征图像进行分块。对分块后的子图像进行提取SIFT特征的操作,将得到的Gabor特征全部SIFT向量级联作为最终特征向量。使用主成分分析方法对得到的最终特征向量进行降维处理,随后使用最小二乘支持向量机进行训练识别。在FERET人脸数据库中进行的实验结果表明,相对于传统单一的人脸识别方法,利用本文方法在姿态变化和光照干扰情况下对人脸识别的准确率达到98.1%,证明了新算法的有效性。

关键词: 人脸识别, Gabor特征, SIFT特征, 特征点匹配, PCA, 支持向量机

Abstract:

Position variation and illumination interference affect the accuracy and efficiency of face recognition. To solve the problem, a new method of feature extraction combining the Gabor feature and SIFT feature was proposed in this paper. Gabor feature of face images from multiple scales and directions were extracted and divided into sub-images of the same size. The SIFT features were extracted from the partitioned sub-images, and all SIFT vectors of the obtained Gabor features were cascaded as the final feature vectors. Principal component analysis method was used to reduce the dimension of the final eigenvectors, and then the least squares support vector machine was used for training and recognition of images. Experimental results of tests in the FERET face database showed that compared with the traditional single face recognition method, the accuracy of face recognition was 98.1% under the change of position and illumination interference, which proved the effectiveness of the new algorithm.

Key words: face recognition, Gabor feature, SIFT feature, feature point matching, PCA, SVM

中图分类号:

TN957.52

周柱,甘屹,孙福佳. 一种融合Gabor+SIFT特征的人脸识别算法[J]. 电子科技, 2019, 32(4): 1-5.

ZHOU Zhu,GAN Yi,SUN Fujia. Research of Face Recognition Method Based on Gabor and SIFT Features[J]. Electronic Science and Technology, 2019, 32(4): 1-5.

图/表 8

图1

图2

图3

图4

图5

图6

表1

表2

参考文献 17

[1]	邹国锋, 傅桂霞, 李海涛 , 等. 多姿态人脸识别综述[J]. 模式识别与人工智能, 2015,28(7):613-625. doi: 10.16451/j.cnki.issn1003-6059.201507005
	Zou Guofeng, Fu Guixia, Li Haitao , et al. A survey of multi-pose face recognition[J]. Pattern Recognition and Artificial Intelligence, 2015,28(7):613-625. doi: 10.16451/j.cnki.issn1003-6059.201507005
[2]	刘军, 景晓军, 孙松林 , 等. 一种用于人脸识别的基于主导近邻像素的局部Gabor空间直方图特征[J]. 北京邮电大学学报, 2015,38(1):51-54. doi: 10.13190/j.jbupt.2015.01.010
	Liu Jun, Jing Xiaojun, Sun Songlin , et al. Feature of local gabor spatial histogram based on dominant neighboring pixel for face recognition[J]. Journal of Beijing University of Posts and Telecommunications, 2015,38(1):51-54. doi: 10.13190/j.jbupt.2015.01.010
[3]	李文辉, 高璐, 林逸峰 , 等. 特征选择模糊加权多通道Gabor人脸识别[J]. 湖南大学学报:自然科学版, 2013,40(4):87-93. doi: 10.3969/j.issn.1674-2974.2013.04.015
	Li Wenhui, Gao Lu, Lin Yifeng , et al. Feature selection fuzzy weighted Multi-Gabor face recognition[J]. Journal of Hunan University:Natural Sciences, 2013,40(4):87-93. doi: 10.3969/j.issn.1674-2974.2013.04.015
[4]	李鹤宇, 王青 . 一种具有实时性的SIFT特征提取算法[J]. 宇航学报, 2017,38(8):865-871. doi: 10.3873/j.issn.1000-1328.2017.08.011
	Li Heyu, Wang Qin . A real-time SIFT feature extraction algorithm[J]. Journal of Astronautics, 2017,38(8):865-871. doi: 10.3873/j.issn.1000-1328.2017.08.011
[5]	刘斌, 徐岩, 米强 , 等. 融合Gabor和Gist特征的人脸识别[J]. 计算机工程与应用, 2017(15):217-221.
	Liu Bin, Xu Yan, Mi Qiang , et al. Fusing Gabor and Gist features for face recognition[J]. Computer Engineering and Applications, 2017,53(15):217-221.
[6]	魏月纳, 吴锡生 .基于 Gabor 融合和分块处理的人脸识别算法[J]. 计算机工程与设计, 2017,38(3):719-723. doi: 10.16208/j.issn1000-7024.2017.03.030
	Wei Yuena, Wu Xisheng . Face recognition algorithm based on Gabor feature fusion and block processing[J]. Computer Engineering and Design, 2017,38(3):719-723. doi: 10.16208/j.issn1000-7024.2017.03.030
[7]	詹曙, 张启祥, 蒋建国 , 等. 基于Gabor特征核协作表达的三维人脸识别[J]. 光子学报, 2013,42(12):1448-1453.
	Zhan Shu, Zhang Qixiang, Jiang Jianguo , et al. 3D face recognition by kernel collaborative representation based on Gabor feature[J]. Acta Photonica Sinica, 2013,42(12):1448-1453.
[8]	Lades M, Vorbruggen J C, Buhmann J , et al. Distortion invariant object recognition in the dynamic link architecture[J]. IEEE Transactions on Computers, 1993,42(3):300-311. doi: 10.1109/12.210173
[9]	Lowe D G, Lowe D G . Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004,60(2):91-110. doi: 10.1023/B:VISI.0000029664.99615.94
[10]	黄华盛, 杨阿庆 . 基于PCA算法的人脸识别[J]. 电子科技, 2015,28(8):98-101. doi: 10.16180/j.cnki.issn1007-7820.2015.08.029
	Huang Huasheng, Yang Aqing . Face recognition based on PCA algorithm[J]. Electronic Science and Technology, 2015,28(8):98-101. doi: 10.16180/j.cnki.issn1007-7820.2015.08.029
[11]	邢玲, 冯倩, 穆国旺 . 基于卷积神经网络和PCA的人脸识别[J]. 河北工业大学学报, 2016,45(5):44-49. doi: 10.14081/j.cnki.hgdxb.2015.05.007
	Xing Ling, Feng Qian, Mu Guowang , et al. Face recognition based on convolution neural network and PCA[J]. Journal of Hebei University of Technology, 2016,45(5):44-49. doi: 10.14081/j.cnki.hgdxb.2015.05.007
[12]	Javed A . Face recognition based on principal component analysis[J]. International Journal of Image,Graphics and Signal Processing (IJIGSP), 2013,5(2):152-159.
[13]	刘红健, 胡蓉 . K近邻和最小二乘支持向量机相融合的人脸识别[J]. 激光杂志, 2014(11):23-25. doi: 10.14016/j.cnki.jgzz.2014.11.023
	Liu Hongjian, Hu Rong . Face recognition based on K nearest neighbor and least square support vector machine[J]. Laser Journal, 2014(11):23-25. doi: 10.14016/j.cnki.jgzz.2014.11.023
[14]	Phillips P J, Moon H, Rauss P J , et al. The FERET evaluation methodology for face recognition algorithm[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2000,22(10):1090-1104. doi: 10.1109/34.879790
[15]	Sun X, Xu H, Zhao C, et al. Facial expression recognition based on histogram sequence of local Gabor binary patterns [C].Chengdu:IEEE Conference on Cybernetics and Intelligent Systems, 2008.
[16]	毋立芳, 侯亚希, 许晓 , 等. 基于紧致全姿态二值SIFT的人脸识别[J]. 仪器仪表学报, 2015,36(4):736-742.
	Wu Lifang, Hou Yaxi, Xu Xiao , et al. Compact complete pose binary SIFT for face recognition with pose variation[J]. Chinese Journal of Scientific Instrument, 2015,36(4):736-742.
[17]	Gu W, Xiang C, Venkatesh Y V , et al. Facial expression recognition using radial encoding of local Gabor features and classifier synjournal[J]. Pattern Recognition, 2012,45(1):80-91. doi: 10.1016/j.patcog.2011.05.006

样本数量	平均识别率
样本数量	文献[15]	文献[16]	文献[5]	文献[17]	本文算法
2	92.9%	89.9%	90.2%	90.8%	92.5%
4	95.7%	90.7%	91.9%	91.3%	93.9%
6	96.8%	91.2%	93.7%	92.2%	96.3%
8	98.5%	94.4%	94.9%	93.6%	97.8%

样本数量	平均识别率
样本数量	文献[15]	文献[16]	文献[5]	文献[17]	本文算法
2	85.2%	90.2%	81.1%	82.7%	92.5%
4	86.4%	93.8%	83.5%	83.6%	94.9%
6	87.8%	94.3%	86.2%	85.3%	97.3%
8	89.4%	96.6%	88.5%	87.9%	98.1%