Generative Data Augmentation applied to Face Recognition

In this paper, we present a data augmentation method whose goal is to generate face images and maximize faces variation in the training set. The main objective is to break free from the traditional data augmentation techniques used in deep neural networks such as geometric and photometric transformations. Our method consists in generating face images using Deep Convolutional Generative Adversarial Networks (DC-GAN) feed with light pose variations of the face in 2D plane. Its a selective feature space augmentation. Then, we apply face resolution enhancement based on Enhanced Super Resolution GAN (ESRGAN), since the generated faces are inferior and noisy. As a final step, we perform face verification using Deep Convolutional Neural Networks (CNNs) to confirm the robustness of the used pipeline. The found results achieves comparable performance in comparison with the state-of-the-art methods.

[1]  M. Neji,et al.  Face Identification Using Data Augmentation Based on the Combination of DCGANs and Basic Manipulations , 2022, Inf..

[2]  Marwa Jabberi.  3D Face Alignment Method Applied to Face Recognition , 2021 .

[3]  V. Arulkumar,et al.  An Intelligent Face Detection by Corner Detection using Special Morphological Masking System and Fast Algorithm , 2021, 2021 2nd International Conference on Smart Electronics and Communication (ICOSEC).

[4]  Abdullah-Al-Mamun,et al.  Human Face Detection Techniques: A Comprehensive Review and Future Research Directions , 2021, Electronics.

[5]  Abdullah Aman Khan,et al.  Classical and modern face recognition approaches: a complete review , 2020, Multim. Tools Appl..

[6]  Yao Zou,et al.  Face Image Age Estimation Based on Data Augmentation and Lightweight Convolutional Neural Network , 2020, Symmetry.

[7]  Chris A. Mattmann,et al.  Deep Facial Recognition using Tensorflow , 2019, 2019 IEEE/ACM Third Workshop on Deep Learning on Supercomputers (DLS).

[8]  Nitin Kumar,et al.  Incremental methods in face recognition: a survey , 2019, Artificial Intelligence Review.

[9]  Tal Hassner,et al.  Face-Specific Data Augmentation for Unconstrained Face Recognition , 2019, International Journal of Computer Vision.

[10]  Xinbo Gao,et al.  Data Augmentation-Based Joint Learning for Heterogeneous Face Recognition , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[11]  Shifeng Zhang,et al.  Selective Refinement Network for High Performance Face Detection , 2018, AAAI.

[12]  Stefanos Zafeiriou,et al.  ArcFace: Additive Angular Margin Loss for Deep Face Recognition , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Shiguang Shan,et al.  AttGAN: Facial Attribute Editing by Only Changing What You Want , 2017, IEEE Transactions on Image Processing.

[14]  Yu Qiao,et al.  ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks , 2018, ECCV Workshops.

[15]  Bernhard Egger,et al.  Training Deep Face Recognition Systems with Synthetic Data , 2018, ArXiv.

[16]  Xing Ji,et al.  CosFace: Large Margin Cosine Loss for Deep Face Recognition , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[17]  Vikram Mutneja,et al.  Modified Viola–Jones algorithm with GPU accelerated training and parallelized skin color filtering-based face detection , 2019, Journal of Real-Time Image Processing.

[18]  Amos J. Storkey,et al.  Data Augmentation Generative Adversarial Networks , 2017, ICLR 2018.

[19]  Bhiksha Raj,et al.  SphereFace: Deep Hypersphere Embedding for Face Recognition , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[21]  Xi Zhou,et al.  Data augmentation for face recognition , 2017, Neurocomputing.

[22]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Tal Hassner,et al.  Do We Really Need to Collect Millions of Faces for Effective Face Recognition? , 2016, ECCV.

[24]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

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

[26]  Erik Learned-Miller,et al.  Labeled Faces in the Wild : Updates and New Reporting Procedures , 2014 .

[27]  Richard Szeliski,et al.  Efficient preconditioning of laplacian matrices for computer graphics , 2013, ACM Trans. Graph..

[28]  David J. Kriegman,et al.  Localizing Parts of Faces Using a Consensus of Exemplars , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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