多层次深度网络融合人脸识别算法<sup>*</sup>

doi:10.16451/j.cnki.issn1003-6059.201705007

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (909 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Discriminative facial features can be obtained by deep learning model. Therefore, combining the deep learning, a multi-level deep network extraction model for fusion feature is proposed. In the proposed model, the pooling layer is added after subspace mapping based on deep subspace model, so that the feature dimension is reduced with texture details preserving and local transformation robustness.Meanwhile, face region is divided into 5 parts according to facial feature point achieved by face alignment algorithm. Based on multi-level classification strategy, the global network is firstly trained using the whole face image to obtain five candidate labels for test sample. Then, the local face block is put into sub-network to obtain local representation and test samples are classified in the candidate labels. Experimental results show that the model combined with the local features and global features achieves better accuracy and robustness in the aspect of the illumination, expression, occlusion, etc. Moreover, adding pooling structure and the two-step discrimination algorithm effectively improve the recognition efficiency.

Key words： Deep Learning Subspace Pooling Multi-level Fusion

Received: 25 November 2016

ZTFLH:

TP 391.4

About author:: (HU Zhengping(Corresponding author), born in 1970, Ph.D., professor. His research interests include pattern recognition.)
(HE Wei, born in 1993, master student. Her research interests include deep lear-ning.)
(WANG Meng, born in 1982, Ph.D. candidate. Her research interests include pattern recognition.)
(SUN Zhe, born in 1990, Ph.D. candidate. Her research interests include sparse representation classification.)

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	HU Zhengping
	HE Wei
	WANG Meng
	SUN Zhe

Cite this article:

HU Zhengping,HE Wei,WANG Meng等. Multi-level Deep Network Fused for Face Recognition[J]. , 2017, 30(5): 448-455.

URL:

http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.201705007 OR http://manu46.magtech.com.cn/Jweb_prai/EN/Y2017/V30/I5/448

[1] TURK M, PENTLAND A. Eigenfaces for Recognition. Journal of Cognitive Neuroscience, 1991, 3(1): 71-86.
[2] BELHUMEUR P N, HESPANHA J P, KRIEGMAN D J. Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(7): 711-720.
[3] LEI Z, LI S Z, CHU R F, et al. Face Recognition with Local Gabor Textons // Proc of the International Conference on Advances in Biometrics. Berlin, Germany: Springer, 2007: 49-57.
[4] AHONEN T, HADID A, PIETIKAINEN M. Face Description with Local Binary Patterns: Application to Face Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(12): 2037-2041.
[5] LECUN Y, BENGIO Y, HINTON G. Deep Learning. Nature, 2015,
521(7553): 436-444.
[6] 郭丽丽,丁世飞.深度学习研究进展.计算机科学, 2015, 42(5): 28-33.
(GUO L L, DING S F. Research Progress of Deep Learning. Computer Science, 2015, 42(5): 28-33.)
[7] OUYANG W L, WANG X G, ZENG X Y, et al. DeepID-net: Deformable Deep Convolutional Neural Networks for Object Detection // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2015: 2403-2412.
[8] HE S F, LAU R W H, LIU W X, et al. SuperCNN: A Superpixelwise Convolutional Neural Network for Salient Object Detection. International Journal of Computer Vision, 2015, 115(3): 330-344.
[9] 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.
[10] HAAVISTO M, KAARNA A, LENSU L. Deep Learning for Facial Keypoints Detection // Proc of the 10th International Conference on Computer Vision Theory and Applications. Berlin, Germany: Springer-Verlag, 2015: 289-296.
[11] HE K M, ZHANG X Y, REN S Q, et al. Deep Residual Learning for Image Recognition // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2016: 770-778.
[12] 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.
[13] SCHROFF F, KALENICHENKO 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.
[14] REN S Q, HE K M, GIRSHICH R, et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks[C/OL]. [2016-10-31]. https://arxiv.org/pdf/1506.01497.pdf.
[15] CHAN T H, JIA K, GAO S, et al. PCANet: A Simple Deep Learning Baseline for Image Classification. IEEE Transactions on Image Processing, 2015, 24(12): 5017-5032.
[16] XIONG C, LIU L Q, ZAHO X W, et al. Convolutional Fusion Network for Face Verification in the Wild. IEEE Transactions on Circuits & Systems for Video Technology, 2015, 26(3): 517-528.
[17] SHI Z L, YE Y D, WU Y P. Rank-Based Pooling for Deep Convolutional Neural Networks. Neural Networks, 2016, 83: 21-31.
[18] HE K M, ZHANG X Y, REN S Q, et al. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1904-1916.
[19] HU G S, YANG Y X, YI D, et al. When Face Recognition Meets with Deep Learning: An Evaluation of Convolutional Neural Networks for Face Recognition // Proc of the IEEE International Conference on Computer Vision Workshops. Washington, USA: IEEE, 2015: 384-392.