Advertisement

Reconstructing Obfuscated Human Faces with Conditional Adversarial Network

  • Sumit Rajgure
  • Maheep MahatEmail author
  • Yash Mekhe
  • Sangita Lade
Conference paper
  • 16 Downloads
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1101)

Abstract

In today’s era of advanced forensic and security technologies, the problem of identifying a human face from a low-quality image obtained from low-quality hardware or other reasons is a major challenge. Trying to extract meaningful information from these images is very difficult. These low-quality images have mainly two kinds of distortion in it, i.e. blurring and pixelation. Prior attempts have been done using different machine learning and deep learning techniques, but the desired high-quality images are not obtained. In this paper, we have used the conditional adversarial network to reconstruct highly obfuscated human faces. Various previous works on the conditional adversarial network have suggested it as a general-purpose solution for image-to-image translation problems. The conditional adversarial network is able to learn mapping from the provided input image to resulting output image. It is also able to learn the loss function to train the mapping. We have examined the result of this model using pixel loss function which gives the exact mapping of obtained high-quality human face with ground truth; furthermore, we have examined the capabilities of this model with very high-level obfuscated images.

Keywords

Generator Discriminator Generative adversarial network ReLu U-Net PatchGAN CNN 

References

  1. 1.
    Lander, K., and L. Chuang. 2005. Why are moving faces easier to recognize? Visual Cognition 12 (3): 429–442.CrossRefGoogle Scholar
  2. 2.
    Lander, K., V. Bruce, and H. Hill. 2001. Evaluating the effectiveness of pixelation and blurring on masking the identity of familiar faces. Applied Cognitive Psychology 15 (1): 101–116.CrossRefGoogle Scholar
  3. 3.
    Gross, R., L. Sweeney, F. de la Torre, and S. Baker. 2006. Model-based face de-identification. In 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW’06), 161–161, June 2006.Google Scholar
  4. 4.
    McPherson, R., R. Shokri, and V. Shmatikov. 2016. Defeating image obfuscation with deep learning. CoRR, abs/1609.00408.Google Scholar
  5. 5.
    Yang, C.-Y., C. Ma, and M.-H. Yang. 2014. Single-image superresolution: A benchmark. In Proceedings of European Conference on Computer Vision.Google Scholar
  6. 6.
    Radford, A., L. Metz, and S. Chintala. 2016. Unsupervised representation learning with deep convolutional generative adversarial networks. ICLR 2 (3): 16.Google Scholar
  7. 7.
    Ioffe, S., and C. Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. ICML 3: 4.Google Scholar
  8. 8.
    Pathak, D., P. Krahenbuhl, J. Donahue, T. Darrell, and A.A. Efros. Context encoders: Feature learning by inpainting. In CVPR, 2, 3, 13, 17.Google Scholar
  9. 9.
    Wang, X., and A. Gupta. 2016. Generative image modeling using style and structure adversarial networks. ECCV 2 (3): 5.Google Scholar
  10. 10.
    Johnson, J., A. Alahi, and L. Fei-Fei. 2016. Perceptual losses for real-time style transfer and super-resolution. ECCV 2: 3.Google Scholar
  11. 11.
    Zhou, Y., and T.L. Berg. 2016. Learning temporal transformations from time-lapse videos. ECCV 2 (3): 8.Google Scholar
  12. 12.
    Yoo, D., N. Kim, S. Park, A.S. Paek, and I.S. Kweon. 2016. Pixellevel domain transfer. ECCV 2: 3.Google Scholar
  13. 13.
    Hinton, G.E., and R.R. Salakhutdinov. 2006. Reducing the dimensionality of data with neural networks. Science 313 (5786): 504–507.MathSciNetCrossRefGoogle Scholar
  14. 14.
    Ronneberger, O., P. Fischer, and T. Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. MICCAI 2: 3.Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Sumit Rajgure
    • 1
  • Maheep Mahat
    • 1
    Email author
  • Yash Mekhe
    • 1
  • Sangita Lade
    • 1
  1. 1.Department of Computer EngineeringVishwakarma Institute of TechnologyPuneIndia

Personalised recommendations