Learning Multi-channel Deep Feature Representations for Face Recognition

Deep learning provides a natural way to obtain feature representations from data without relying on hand-crafted descriptors. In this paper, we propose to learn deep feature representations using unsupervised and supervised learning in a cascaded fashion to produce generically descriptive yet class specic features. The proposed method can take full advantage of the availability of large-scale unlabeled data and learn discriminative features (supervised) from generic features (unsupervised). It is then applied to multiple essential facial regions to obtain multi-channel deep facial representations for face recognition. The ecacy of the proposed feature representations is validated on both controlled (i.e., extended Yale-B, Yale, and AR) and uncontrolled (PubFig) benchmark face databases. Experimental results show its eectiveness.

[1]  Anderson Rocha,et al.  Person-Specific Subspace Analysis for Unconstrained Familiar Face Identification , 2012, BMVC.

[2]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Mohammed Bennamoun,et al.  Linear Regression for Face Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Jianzhong Wang,et al.  An adaptively weighted sub-pattern locality preserving projection for face recognition , 2010, J. Netw. Comput. Appl..

[5]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[6]  A. Martínez,et al.  The AR face databasae , 1998 .

[7]  Jiang-She Zhang,et al.  Face recognition using Elasticfaces , 2012, Pattern Recognit..

[8]  Geoffrey E. Hinton.  Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[9]  Lei Zhang,et al.  Sparse representation or collaborative representation: Which helps face recognition? , 2011, 2011 International Conference on Computer Vision.

[10]  David Cox,et al.  Scaling up biologically-inspired computer vision: A case study in unconstrained face recognition on facebook , 2011, CVPR 2011 WORKSHOPS.

[11]  Honglak Lee,et al.  Learning hierarchical representations for face verification with convolutional deep belief networks , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Matti Pietikäinen,et al.  Face Description with Local Binary Patterns: Application to Face Recognition , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[14]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[15]  David J. Kriegman,et al.  From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Xiaogang Wang,et al.  Deep Learning Face Representation by Joint Identification-Verification , 2014, NIPS.

[17]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Jian Sun,et al.  Face recognition with learning-based descriptor , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[19]  Jian Yang,et al.  Robust sparse coding for face recognition , 2011, CVPR 2011.

[20]  Aleix M. Martinez,et al.  The AR face database , 1998 .

[21]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[22]  Esa Rahtu,et al.  BSIF: Binarized statistical image features , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[23]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[24]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[25]  Stan Davis,et al.  Comparison of Parametric Representations for Monosyllabic Word Recognition in Continuously Spoken Se , 1980 .

[26]  Shree K. Nayar,et al.  Attribute and simile classifiers for face verification , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[27]  Wei Jia,et al.  Discriminant sparse neighborhood preserving embedding for face recognition , 2012, Pattern Recognit..

[28]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[29]  Ming Yang,et al.  DeepFace: Closing the Gap to Human-Level Performance in Face Verification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[30]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[31]  Matti Pietikäinen,et al.  Learning Discriminant Face Descriptor , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  Xiaogang Wang,et al.  Deep Learning Identity-Preserving Face Space , 2013, 2013 IEEE International Conference on Computer Vision.

[33]  David J. Kriegman,et al.  Recognition using class specific linear projection , 1997 .

[34]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[35]  Anderson Rocha,et al.  Learning Person-Specific Representations From Faces in the Wild , 2014, IEEE Transactions on Information Forensics and Security.

[36]  Chengjun Liu,et al.  Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition , 2002, IEEE Trans. Image Process..