基于深度自编码器的单样本人脸识别<sup>*</sup>

doi:10.16451/j.cnki.issn1003-6059.201704006

摘要
图/表
参考文献
相关文章 (2)

全文: PDF (962 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要由于每个目标仅有一幅已知样本,无法描述目标的类内变化,诸多人脸识别算法在解决单样本人脸识别问题时识别性能较低.因此文中提出基于深度自编码器的单样本人脸识别算法.算法首先采用所有已知样本训练深度自编码器,得到广义深度自编码器,然后使用每个单样本目标的单个样本微调广义深度自编码器,得到特定类别的深度自编码器.识别时,将识别图像输入每个特定类别的深度自编码器,得到包含与测试图像相同类内变化的该类别的重构图像,使用重构图像训练Softmax回归模型,分类测试图像.在公共测试库上进行测试,并与其它算法在相同环境下进行对比,结果表明文中算法在获得更优识别率的同时,识别一幅图像所需平均时间更少.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	张彦
	彭华

关键词 ：单样本人脸识别, 深度自编码器, 样本重构

Abstract：Since there is only one sample for each subject, it is hard to describe intra-class variations of the subject. The performance of state-of-the-art face recognition algorithms declines in one sample per person(OSPP) face recognition. In this paper, an OSPP face recognition algorithm based on deep autoencoder(OSPP-DA) is proposed. In OSPP-DA, deep autoencoder is trained by all the images in the gallery firstly, and a generalized deep autoencoder(GDA) is generated. Then, the GDA is fine-tuned by the single sample of the subject, and a class-specified deep autoencoder(CDA) is obtained. For classification, query images are input to CDAs and the reconstruction samples of the corresponding subjects have the same intra-class variation as query images. A Softmax regression model is trained by the reconstruction samples and the query images are identified by the Softmax regression model. Experiments on public testing database are conducted and the results show the validity of OSPP-DA. Compared with some state-of-the-art algorithms, the proposed algorithm produces better performance with less time.

Key words： One Sample per Person Face Recognition Deep Autoencoder Sample Reconstruction

ZTFLH:

TP 391.4

基金资助:河南省教育厅科学技术研究重点项目(No.12A510027)资助

作者简介: 张彦,女,1975年生,博士研究生,讲师,主要研究方向为图像处理、模式识别.E-mail: miaomiao9323@163.com.
彭华(通讯作者),男,1973年生,博士,教授,主要研究方向为软件无线电、通信信号处理.E-mail:pengh139@139.com.

引用本文:

张彦，彭华. 基于深度自编码器的单样本人脸识别^*[J]. 模式识别与人工智能, 2017, 30(4): 343-352. ZHANG Yan, PENG Hua. One Sample per Person Face Recognition Based on Deep Autoencoder. , 2017, 30(4): 343-352.

链接本文:

http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.201704006 或 http://manu46.magtech.com.cn/Jweb_prai/CN/Y2017/V30/I4/343

[1] TAN X Y , CHEN S C , ZHOU Z H, et al. Face Recognition from a Single Image per Person: A Survey. Pattern Recognition, 2006, 39(9): 1725-1745.
[2] ETEMAD K, CHELLAPPA R. Discriminant Analysis for Recognition of Human Face Images. Journal of the Optical Society of America A, 1997, 14(8): 1724-1733.
[3] ROWEIS S T, SAUL L K. Nonlinear Dimensionality Reduction by Locally Linear Embedding. Science, 2000, 290(5500): 2323-2326.
[4] HE X F, NIYOGI P. Locality Preserving Projections // THRUN S, SAUL L K, SCHLKOPF P B, eds. Advances in Neural Information Processing Systems 16. Cambridge, USA: The MIT Press, 2003: 153-160.
[5] WRIGHT J, YANG A Y, GANESH A, et al. Robust Face Recognition via Sparse Representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(2): 210-227.
[6] YANG J, ZHANG D, FRANGI A F, et al. Two-Dimensional PCA: A New Approach to Appearance-Based Face Representation and Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(1): 131-137.
[7] DENG W H, HU J N, GUO J, et al. Robust, Accurate and Efficient Face Recognition from a Single Training Image: A Uniform Pursuit Approach. Pattern Recognition, 2010, 43(5): 1748-1762.
[8] LU J W, TAN Y P, WANG G. Discriminative Multimanifold Analysis for Face Recognition from a Single Training Sample per Person. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(1): 39-51.
[9] LIU F, TAN J H, SONG Y, et al. Local Structure Based Sparse Representation for Face Recognition with Single Sample per Person // Proc of the IEEE International Conference on Image Processing, Washington, USA: IEEE, 2014: 713-717.
[10] WANG B, LI W F, LI Z M, et al. Adaptive Linear Regression for Single-Sample Face Recognition. Neurocomputing, 2013, 115: 186-191.
[11] HUANG D A, WANG Y C F. With One Look: Robust Face Re-
cognition Using Single Sample per Person // Proc of the 21st ACM International Conference on Multimedia. New York, UWA: ACM, 2013: 601-604.
[12] DENG W H, HU J N, GUO J. Extended SRC: Undersampled Face Recognition via Intraclass Variant Dictionary. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(9): 1864-1870.
[13] DENG W H, HU J N, GUO J. In Defense of Sparsity Based Face Recognition // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2013: 399-406.
[14] CHEN S B, DING C H Q, LUO B. Extended Linear Regression for Undersampled Face Recognition. Journal of Visual Communication and Image Representation, 2014, 25(7): 1800-1809.
[15] JI H K, SUN Q S, JI Z X, et al. Collaborative Probabilistic Labels for Face Recognition from Single Sample per Person. Pattern Re-
cognition, 2017, 62: 125-134.
[16] HINTON G E, SALAKHUTDINOV R R. Reducing the Dimensionality of Data with Neural Networks. Science, 2006, 313(5786): 504-507.
[17] KHAN S H, BENNAMOUN M, SOHEL F, et al. Automatic Sha-
dow Detection and Removal from a Single Image. IEEE Transactions on Pattern analysis and Machine Intelligence, 2016, 38(3): 431-446.
[18] DONG C, LOY C C, HE K M, et al. Image Super-Resolution Using Deep Convolutional Networks.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(2): 295-307.
[19] ZHAO R, OUYANG W L, LI H S, et al. Saliency Detection by Multi-context Deep Learning // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2015: 1265-1274.
[20] SUN Y, WANG X G, TANG X O. Deep Learning Face Representation from Predicting 10000 Classes // Proc of the IEEE Confe-
rence on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2014: 1891-1898.
[21] SUN Y, WANG X G, TANG X O. Deeply Learned Face Representations Are Sparse, Selective, and Robust // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2015: 2892-2900.
[22] SCHROFF F, KALENICTBHENKO D, PHILBIN J. FaceNet: A Unified Embedding for Face Recognition and Clustering // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2015: 815-823.
[23] SUN Y, CHEN Y H, WANG X G, et al. Deep Learning Face Representation by Joint Identification Verification // Proc of the 27th International Conference on Neural Information Processing Systems. Cambridge, USA: The MIT Press, 2014: 1988-1996.
[24] GAO S H, ZHANG Y T, JIA K, et al. Single Sample Face Recognition via Learning Deep Supervised Autoencoders. IEEE Transactions on Information Forensics and Security, 2015, 10(10): 2108-2118.
[25] ARRIBAS J I, CID-SUEIRO J, ADALI T, et al. Estimates of Constrained Multi-class a Posteriori Probabilities in Time Series Problems with Neural Networks // Proc of the International Joint Con-
ference on Neural Networks. Washington, USA: IEEE, 1999:1560-1561.
[26] HINTON G E. A Practical Guide to Training Restricted Boltzmann Machines. 2nd Edition. Berlin, Germany: Springer, 2012.
[27] RUMELHART D E, HINTON G E, WILLIAMS R J. Learning Representations by Back-Propagating Errors. Nature,1986,323(6088): 533-536.
[28] NIELSEN M A. Neural Networks and Deep Learning[M/OL]. [2015-04-08]. http://neuralnetworksanddeeplearning.com.
[29] NG A, NGIAM J Q, FOO C Y. Data Preprocessing[EB/OL].[2015-05-15]. http://ufldl.stanford.edu/wiki/index.php/Data_Preprocessing.
[30] NG A, NGIAM J Q, FOO C Y. Whitening[EB/OL]. [2015-05-20]. http://ufldl.stanford.edu/wiki/index.php/Whitening.
[31] ERHAN D, BENGIO Y, COURVILLE A, et al. Visualizing Higher-Layer Features of a Deep Network. Technical Report, 1341. Montreal, Canada: University of Montreal, 2009.