Detecting Digital Photo Tampering with Deep Learning

  • Mitchell B. Singleton
  • Qingzhong LiuEmail author
Conference paper
Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 251)


The tools to tamper with digital photographs have become easier to use by the lay person and techniques have evolved that make detection of tampering more difficult, there is a clear need to not only discover novel ways to distinguish the difference between real and fake, but also to make the detection quicker and easier. Using content-aware resizing, which is also known as image retargeting, seam carving, content-aware rescaling, liquid rescaling, or liquid resizing, allows for changing the resolution of an image while keeping the content unchanged in the image. In this paper, the retraining of Inception ResNet v2, one of the best object detection deep learning classifiers, is undertaken to look at classifications of untampered versus tampered photos via seam removal.


Photography Detection of tampering Detection of modification Detection of falsification Deep learning 



We highly appreciate the support for this study from the National Science Foundation under Award #1318688 and from the SHSU Office of Research and Sponsored Programs under an Enhanced Research Grant.


  1. 1.
    Hsu, C.-M., Lee, J.-C., Chen, W.-K.: An efficient detection algorithm for copy-move forgery. Presented at the May (2015)Google Scholar
  2. 2.
    Chen, C., Shi, Y.Q., Su, W.: A machine learning based scheme for double JPEG compression detection. In: 2008 19th International Conference on Pattern Recognition. ICPR 2008, pp. 1–4. IEEE (2008)Google Scholar
  3. 3.
    Chen, Y.-L., Hsu, C.-T.: Detecting recompression of JPEG images via periodicity analysis of compression artifacts for tampering detection. IEEE Trans. Inf. Forensics Secur. 6, 396–406 (2011). Scholar
  4. 4.
    Dirik, A.E., Memon, N.: Image tamper detection based on demosaicing artifacts. Presented at the November (2009)Google Scholar
  5. 5.
    Farid, H.: Image forgery detection. IEEE Signal Process. Mag. 26, 16–25 (2009). Scholar
  6. 6.
    Liu, Q.: An approach to detecting JPEG down-recompression and seam carving forgery under recompression anti-forensics. Pattern Recogn. 65, 35–46 (2017)CrossRefGoogle Scholar
  7. 7.
    Liu, Q.: An improved approach to detecting JPEG seam carving under recompression. IEEE Trans. Circuits Syst. Video Technol. (in Press)Google Scholar
  8. 8.
    Avidan, S., Shamir, A.: Seam carving for content-aware image resizing. ACM Trans. Graph. 26, 10 (2007). Scholar
  9. 9.
    Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.: Inception-v4, inception-ResNet and the impact of residual connections on learning. arXiv:160207261 Cs. (2016)
  10. 10.
    Szegedy, C., et al.: Going deeper with convolutions. Presented at the June (2015)Google Scholar
  11. 11.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv:1502.03167 (2015)
  12. 12.
    Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. Presented at the June (2016)Google Scholar
  13. 13.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. Presented at the June (2016)Google Scholar
  14. 14.
    Alemi, A.: Improving inception and image classification in TensorFlow,
  15. 15.
    Bunk, J., et al.: Detection and localization of image forgeries using resampling features and deep learning. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1881–1889. IEEE (2017)Google Scholar
  16. 16.
    Chen, B.-C., Ghosh, P., Morariu, V.I., Davis, L.S.: Detection of metadata tampering through discrepancy between image content and metadata using multi-task deep learning. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1872–1880. IEEE (2017)Google Scholar
  17. 17.
    Shan, J., Li, L.: A deep learning method for microaneurysm detection in fundus images. Presented at the June (2016)Google Scholar
  18. 18.
    Kalpana, K., Amritha, P.P.: Image manipulation detection using deep learning in TensorFlow. Int. J. Control Theory Appl. 9(40), 221–225 (2016)Google Scholar
  19. 19.
    Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. arXiv 1409 (2014)Google Scholar

Copyright information

© ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2018

Authors and Affiliations

  1. 1.Department of Computer ScienceSam Houston State UniversityHuntsvilleUSA

Personalised recommendations