Abstract
This paper proposes a two-dimensional principal component analysis network (2DPCANet), which is a novel deep learning network for face recognition. In our architecture, 2DPCA is employed to learn the filters of multistage layers, and then we exploit binary hashing and the block-wise histograms to generate the local features. Support vector machine (SVM) and extreme learning machine (ELM) are adopted as the classifier. The experimental results obtained on the facial database YALE, XM2VTS, AR, LFW-a, FERET and Extended Yale B show that the recognition performance of 2DPCANet is superior to other reported methods. Another interesting discovery on ELM classifier is that the advantage of ELM being simple and fast will disappear when it is applied to large databases.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Arel I et al (2010) Deep machine learning-a new frontier in artificial intelligence research [research frontier]. Comput Intell Mag, IEEE 5(4):13–18
Belhumeur PN, Hespanha JP, Kriegman DJ (1997) Eigenfaces vs. fisherfaces: recognition using class specific linear projection. IEEE Trans Pattern Anal Mach Intell 19(7):711–720
Burges CJC (1998) A tutorial on support vector machines for pattern recognition. Data Min Knowl Disc 2(2):121–167
Chan TH, Jia K, Gao S et al (2015) PCANet: a simple deep learning baseline for image classification? IEEE Trans Image Process 24(12):5017–5032
Ciresan D, et al. (2012). Multi-column deep neural networks for image classification. Computer Vision and Pattern Recognition (CVPR), 2012 I.E. Conference on, IEEE
Andrew AM (2000) An introduction to support vector machines and other kernel-based learning methods by Nello Christianini and John Shawe-Taylor, Cambridge University Press, Cambridge, 2000, xiii+ 189 pp., ISBN 0-521-78019-5
Feng Z et al (2015) DLANet: a manifold-learning-based discriminative feature learning network for scene classification. Neurocomputing 157:11–21
Georghiades AS et al (2001) From few to many: illumination cone models for face recognition under variable lighting and pose. IEEE Trans Pattern Anal Mach Intell 23(6):643–660
Huang, G.-B., et al. (2004). Extreme learning machine: a new learning scheme of feedforward neural networks. Neural Networks, 2004. Proceedings. 2004 I.E. International Joint Conference on, IEEE
Huang GB, Chen L, Siew CK (2006) Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Trans Neural Netw 17(4):879–892
Huang G-B et al (2006) Extreme learning machine: theory and applications. Neurocomputing 70(1):489–501
Jia Y (2013). Caffe: An open source convolutional architecture for fast feature embedding. Availab le: http://goo.gl/Fo9YO8
Jia Z, Han B, Gao X. (2015). 2DPCANet: Dayside Aurora Classification Based on Deep Learning. CCF Chinese Conference on Computer Vision. Springer Berlin Heidelberg: 323–334.
Krizhevsky A, et al. (2012). Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems: 1097–1105.
Messer K, et al. (1999). XM2VTSDB: The extended M2VTS database. Second international conference on audio and video-based biometric person authentication, Citeseer
Ng CJ, Teoh ABJ (2015) DCTNet: A simple learning-free approach for face recognition. 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA). IEEE, 2015: 761–768.
Phillips PJ, et al. (1996). FERET (face recognition technology) recognition algorithm development and test results. Adelphi: Army Research Laboratory
Phillips PJ et al (2000) The FERET evaluation methodology for face-recognition algorithms. IEEE Trans Pattern Anal Mach Intell 22(10):1090–1104
Smola AJ et al (2004) A tutorial on support vector regression. Stat Comput 14(3):199–222
Widrow B et al (2013) The no-prop algorithm: a new learning algorithm for multilayer neural networks. Neural Netw 37:182–188
Wright J et al (2009) Robust face recognition via sparse representation. IEEE Trans Pattern Anal Mach Intell 31(2):210–227
Yang J, Zhang D, Frangi AF et al (2004) Two-dimensional PCA: a new approach to appearance-based face representation and recognition. IEEE Trans Pattern Anal Mach Intell 26(1):131–137
Zhang D, Zhou Z-H (2005) (2D) 2PCA: two-directional two-dimensional PCA for efficient face representation and recognition. Neurocomputing 69(1):224–231
Zhu, P., et al. (2012). Multi-scale patch based collaborative representation for face recognition with margin distribution optimization. Computer Vision–ECCV 2012, Springer: 822–835
Acknowledgements
The paper is supported by the National Natural Science Foundation of China (Grant No.61373055, 61672265), Industry Project of Provincial Department of Education of Jiangsu Province (Grant No. JH10-28), and Natural Science Foundation of Jiangsu Province, China (Grant No. BK20151358).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Yu, D., Wu, XJ. 2DPCANet: a deep leaning network for face recognition. Multimed Tools Appl 77, 12919–12934 (2018). https://doi.org/10.1007/s11042-017-4923-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-017-4923-3