Deep Joint Face Hallucination and Recognition

Deep models have achieved impressive performance for face hallucination tasks. However, we observe that directly feeding the hallucinated facial images into recog- nition models can even degrade the recognition performance despite the much better visualization quality. In this paper, we address this problem by jointly learning a deep model for two tasks, i.e. face hallucination and recognition. In particular, we design an end-to-end deep convolution network with hallucination sub-network cascaded by recognition sub-network. The recognition sub- network are responsible for producing discriminative feature representations using the hallucinated images as inputs generated by hallucination sub-network. During training, we feed LR facial images into the network and optimize the parameters by minimizing two loss items, i.e. 1) face hallucination loss measured by the pixel wise difference between the ground truth HR images and network-generated images; and 2) verification loss which is measured by the classification error and intra-class distance. We extensively evaluate our method on LFW and YTF datasets. The experimental results show that our method can achieve recognition accuracy 97.95% on 4x down-sampled LFW testing set, outperforming the accuracy 96.35% of conventional face recognition model. And on the more challenging YTF dataset, we achieve recognition accuracy 90.65%, a margin over the recognition accuracy 89.45% obtained by conventional face recognition model on the 4x down-sampled version.

[1]  Harry Shum,et al.  Face Hallucination: Theory and Practice , 2007, International Journal of Computer Vision.

[2]  Shengcai Liao,et al.  Illumination Invariant Face Recognition Using Near-Infrared Images , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

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

[5]  Bruce A. Draper,et al.  A meta-analysis of face recognition covariates , 2009, 2009 IEEE 3rd International Conference on Biometrics: Theory, Applications, and Systems.

[6]  Iryna Gurevych,et al.  Supersense Embeddings: A Unified Model for Supersense Interpretation, Prediction, and Utilization , 2016, ACL.

[7]  Xiaogang Wang,et al.  Hallucinating face by eigentransformation , 2005, IEEE Trans. Syst. Man Cybern. Part C.

[8]  Pong C. Yuen,et al.  Very low resolution face recognition problem , 2010, 2010 Fourth IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS).

[9]  Shengcai Liao,et al.  Learning Face Representation from Scratch , 2014, ArXiv.

[10]  Marwan Mattar,et al.  Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments , 2008 .

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

[12]  William T. Freeman,et al.  Learning low-level vision , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

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

[14]  Thomas S. Huang,et al.  Studying Very Low Resolution Recognition Using Deep Networks , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Takeo Kanade,et al.  Hallucinating faces , 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580).

[16]  Xiaoou Tang,et al.  Image Super-Resolution Using Deep Convolutional Networks , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Yu Qiao,et al.  A Discriminative Feature Learning Approach for Deep Face Recognition , 2016, ECCV.

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

[19]  Yu Qiao,et al.  Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks , 2016, IEEE Signal Processing Letters.

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

[21]  Antonio Torralba,et al.  Ieee Transactions on Pattern Analysis and Machine Intelligence 1 80 Million Tiny Images: a Large Dataset for Non-parametric Object and Scene Recognition , 2022 .

[22]  Xiaogang Wang,et al.  Deeply learned face representations are sparse, selective, and robust , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Z LiStan,et al.  Illumination Invariant Face Recognition Using Near-Infrared Images , 2007 .

[24]  Cao Ming-min Super Resolution Through Neighbor Embedding with Adaptive Neighbor Selection , 2015 .

[25]  Xiaoou Tang,et al.  Deep Cascaded Bi-Network for Face Hallucination , 2016, ECCV.

[26]  Yuning Jiang,et al.  Learning Face Hallucination in the Wild , 2015, AAAI.

[27]  Tal Hassner,et al.  Face recognition in unconstrained videos with matched background similarity , 2011, CVPR 2011.

[28]  Thomas S. Huang,et al.  Image super-resolution as sparse representation of raw image patches , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[29]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[30]  Kyoung Mu Lee,et al.  Accurate Image Super-Resolution Using Very Deep Convolutional Networks , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[31]  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.

[32]  Zhenhua Guo,et al.  Large Margin Coupled Mapping for Low Resolution Face Recognition , 2016, PRICAI.

[33]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).