Abstract：An algorithm of sparse feature extraction model is proposed based on deep and symmetric subspace learning. According to the theory of deep subspace learning, the constraints of symmetry and sparsity are introduced and the deep map network is built to extract features. Firstly, the basic subspace mapping matrix is constructed by minimizing the reconstruction error and the constraints of symmetry and sparsity are introduced for training. Next, the basic subspace model based on deep learning is reformed, and the deep symmetric sparse feature extraction model is built. These feature extraction results from different layers are merged to obtain the multi-layered deep symmetric subspace sparse feature. The experimental results on face databases show that the proposed algorithm achieves high recognition rates and strong robustness in illumination, expression and pose. Furthermore, compared with the convolutional neural networks, the proposed algorithm has the advantages of simple structure and high convergent rate.
胡正平，陈俊岭，王蒙，孙哲. 深层融合对称子空间学习稀疏特征提取模型*[J]. 模式识别与人工智能, 2017, 30(7): 653-662.
HU Zhengping, CHEN Junling, WANG Meng, SUN Zhe. Sparse Feature Extraction Model Based on Deep and Symmetric Subspace Learning. , 2017, 30(7): 653-662.
[1] PAPACHRISTOU K, TEFAS A, PITAS I. Symmetric Subspace Learning for Image Analysis. IEEE Transactions on Image Proce-ssing, 2014, 23(12): 5683-5697. [2] LECUN Y, BENGIO Y, HINTON G. Deep Learning. Nature, 2015, 521(7553): 436-444. [3] LI H X, LI Y, PORIKLI F. DeepTrack: Learning Discriminative Feature Representations by Convolutional Neural Networks for Vi-sual Tracking[C/OL]. [2016-07-25]. http://www.bmva.org/bmvc/2014/files/paper028.pdf. [4] SILVER D, HUANG A, MADDISON C J, et al. Mastering the Game of Go with Deep Neural Networks and Tree Search. Nature, 2016, 529(7587): 484-489. [5] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Imagenet Classification with Deep Convolutional Neural Networks // PEREIRA F, BURGES C J C, BOTTOU L, et al., eds. Advances in Neural Information Processing Systems 25. Cambridge, USA: The MIT Press, 2012: 1097-1105. [6] TAIGMAN Y, YANG M, RANZATO M, et al. DeepFace: Closing the Gap to Human-Level Performance in Face Verification[C/OL]. [2016-07-25]. http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=6909616. [7] SUN Y, WANG X G, TANG X O. Deep Learning Face Representation from Predicting 10,000 Classes[C/OL]. [2016-07-25]. http://mmlab.ie.cuhk.edu.hk/pdf/YiSun_CVPR14.pdf. [8] SUN Y, CHEN Y H, WANG X G, et al. Deep Learning Face Representation by Joint Identification-Verification // GHAHRAMANI Z, WELLING M, CORTES C, et al., eds. Advances in Neural Information Processing Systems 27. Cambridge, USA: The MIT Press, 2014: 1988-1996. [9] SUN Y, WANG X G, TANG X O. Deeply Learned Face Representations Are Sparse, Selective, and Robust[C/OL]. [2016-07-25]. https://arxiv.org/pdf/1412.1265.pdf. [10] LIONG V E, LU J W, WANG G. Face Recognition Using Deep PCA // Proc of the 9th International Conference on Information, Communications and Signal Processing. Washington, USA: IEEE, 2013: 1-5. [11] CHAN T H, JIA K, GAO S H, et al. PCANet: A Simple Deep Learning Baseline for Image Classification? IEEE Transactions on Image Processing, 2015, 24(12): 5017-5032. [12] HUANG J W, YUAN C. Weighted-PCANet for Face Recognition // Proc of the International Conference on Neural Information Processing. Berlin, Germany: Springer, 2015: 246-254. [13] LU J W, WANG G, MOULIN P. Localized Multi-feature Metric Learning for Image Set Based Face Recognition. IEEE Transactions on Circuits and Systems for Video Technology, 2016, 26(3): 529-540. [14] HINTON G E, SALAKHUTDINOV R R. Reducing the Dimensionality of Data with Neural Networks. Science, 2006, 313(5786): 504-507. [15] LECUN Y, JACKEL L D, BOTTOU L, et al. Learning Algorithms for Classification: A Comparison on Handwritten Digit Recognition. Hackensack, USA: World Scientific,1995: 261-276. [16] SIMONYAN K, ZISSERMAN A. Very Deep Convolutional Networks for Large-Scale Image Recognition[C/OL]. [2016-07-25]. https://arxiv.org/pdf/1409.1556.pdf. [17] HE K M, ZHANG X Y, REN S Q, et al. Deep Residual Learning for Image Recognition[C/OL]. [2016-07-25]. https://arxiv.org/pdf/1512.03385v1.pdf. [18] REISFELD D, WOLFSON H, YESHURUN Y. Context-Free Attentional Operators: The Generalized Symmetry Transform. International Journal of Computer Vision, 1995, 14(2): 119-130. [19] HAYFRON-ACQUAH J B, NIXON M S, CARTER J N. Automa-tic Gait Recognition by Symmetry Analysis. Pattern Recognition Letters, 2003, 24(13): 2175-2183. [20] ZHANG L Y, RAZDAN A, FARIN G, et al. 3D Face Authentication and Recognition Based on Bilateral Symmetry Analysis. The Visual Computer, 2006, 22(1): 43-55. [21] LIU Y X, SCHMIDT K L, COHN J F, et al. Facial Asymmetry Quantification for Expression Invariant Human Identification. Computer Vision and Image Understanding, 2003, 91(1): 138-159. [22] SZEGEDY C, LIU W, JIA Y, et al. Going Deeper with Convolutions[C/OL]. [2016-07-25]. https://www.cs.unc.edu/~wliu/papers/GoogLeNet.pdf. [23] LIU B Y, WANG M, FOROOSH H, et al. Sparse Convolutional Neural Networks[C/OL]. [2016-07-25]. http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7298681. [24] LU J W, LIONG V E, WANG G, et al. Joint Feature Learning for Face Recognition. IEEE Transactions on Information Forensics and Security, 2015, 10(7): 1371-1383. [25] WANG D, LU H C. Object Tracking via 2DPCA and l1-Regularization. IEEE Transactions on Signal Processing Letters, 2012, 19(11): 711-714.
2017, Vol. 30 
