Export file:


  • RIS(for EndNote,Reference Manager,ProCite)
  • BibTex
  • Text


  • Citation Only
  • Citation and Abstract

Resampling detection of recompressed images via dual-stream convolutional neural network

1 School of Computer Science and Cybersecurity, Communication University of China, Beijing 100024, China
2 Key Laboratory of Convergent Media and Intelligent Technology (Communication University of China), Ministry of Education, China
3 School of Data Science and Media Intelligence, Communication University of China, Beijing 100024, China

Special Issues: Information Multimedia Hiding & Forensics based on Intelligent Devices

Resampling detection plays an important role in identifying image tampering, such as image splicing. Currently, the resampling detection is still difficult in recompressed images, which are yielded by applying resampling followed by post-JPEG compression to primary JPEG images. Except for the scenario of low quality primary compression, it remains rather challenging due to the widespread use of middle/high quality compression in imaging devices. In this paper, we propose a new convolution neural network (CNN) method to learn the resampling trace features directly from the recompressed images. To this end, a noise extraction layer based on low-order high pass filters is deployed to yield the image residual domain, which is more beneficial to extract manipulation trace features. A dual-stream CNN is presented to capture the resampling trails along different directions, where the horizontal and vertical network streams are interleaved and concatenated. Lastly, the learned features are fed into Sigmoid/Softmax layer, which acts as a binary/multiple classifier for achieving the blind detection and parameter estimation of resampling, respectively. Extensive experimental results demonstrate that our proposed method could detect resampling effectively in recompressed images and outperform the state-of-the-art detectors.
  Article Metrics


1. M. Stamm, M. Wu and K. J. Liu, Information forensics: An overview of the first decade, IEEE Access, 1 (2013), 167–200.

2. H. Farid, Exposing digital forgeries from JPEG ghosts, IEEE T. Inf. Foren. Sec., 4 (2009), 154– 160.

3. W. Luo, J. Huang and G. Qiu, JPEG error analysis and its applications to digital image forensics, IEEE T. Inf. Foren. Sec., 5 (2010), 480–491.

4. G. Cao, Y. Zhao, R. Ni, et al., Contrast enhancement-based forensics in digital images, IEEE T. Inf. Foren. Sec., 9 (2014), 515–525.

5. G. Cao, Y. Zhao, R. Ni, et al., Attacking contrast enhancement forensics in digital images, Sci. China Inform. Sci., 57 (2014), 1–13.

6. G. Cao, L. Huang, H. Tian, et al., Contrast enhancement of brightness-distorted images by improved adaptive gamma correction, Comput. Electr. Eng., 66 (2018), 569–582.

7. F. Ding, G. Zhu, W. Dong, et al., An efficient weak sharpening detection method for image forensics, J. Vis. Commun. Image R., 50 (2018), 93–99.

8. X. Kang, M. Stamm, A. Peng, et al., Robust median filtering forensics using an autoregressive model, IEEE T. Inf. Foren. Sec., 8 (2013), 1456–1468.

9. S. Ye, Q. Sun and E. C. Chang, Detecting digital image forgeries by measuring inconsistencies of blocking artifact, IEEE International Conference on Multimedia and Expo, (2007), 12–15.

10. A. Dirik and N. Memon, Image tamper detection based on demosaicing artifacts, IEEE International Conference on Image Processing, (2009), 1497–1500.

11. P. Ferrara, T. Bianchi, A. De Rosa, et al., Image forgery localization via fine-grained analysis of CFA artifacts, IEEE T. Inf. Foren. Sec., 7 (2012), 1566–1577.

12. I. Amerini, R. Becarelli, R. Caldelli, et al., Splicing forgeries localization through the use of first digit features, IEEE International Workshop on Info. Forensics and Security, (2014), 143–148.

13. M. Huh, A. Liu, A. Owens, et al., Fighting fake news: image splice detection via learned self-consistency, European Conference on Computer Vision, (2018), 101–117.

14. P. Zhou, X. Han, V. Morariu, et al., Learning rich features for image manipulation detection, IEEE Conference on Computer Vision and Pattern Recognition, (2018), 1053–1061.

15. J. Bunk, J. Bappy and T. Mohammed, Detection and localization of image forgeries using resampling features and deep learning, IEEE Conference on Computer Vision and Pattern Recognition Workshops, (2017), 1881–1889.

16. J. Wang, T. Li, X. Luo, et al., Identifying computer generated images based on quaternion central moments in color quaternion wavelet domain, IEEE T. Circ. Syst. Vid., (2018), 1.

17. A. Popescu and H. Farid, Exposing digital forgeries by detecting traces of resampling, IEEE T. Signal Proces., 53 (2005), 758–767.

18. D.Padín, P.ComesanaandF.González, AnSVDapproachtoforensicimageresamplingdetection, European Signal Processing Conference, (2015), 2067–2071.

19. D. Padín, F. González and P. Comesana, A random matrix approach to the forensic analysis of upscaled images, IEEE T. Inf. Foren. Sec., 12 (2017), 2115–2130.

20. Y. Kao, H. Lin, C. Wang, et al., Effective detection for linear up-sampling by factor of fraction, IEEE T. Image Process., 21 (2012), 3443–3453.

21. B. Mahdian and S. Saic, Blind authentication using periodic properties of interpolation, IEEE T. Inf. Foren. Sec., 3 (2008), 529–538.

22. T. Qiao, R. Shi, X. Luo, et al., Statistical model-based detector via texture weight map: application in re-sampling authentication, IEEE T. Multimedia, 21 (2019), 1077–1092.

23. X. Feng, I. J. Cox and G. Doerr, An energy-based method for the forensic detection of re-sampled images, IEEE International Conference on Multimedia and Expo, (2011), 1–6.

24. M. Kirchner, Fast and reliable resampling detection by spectral analysis of fixed linear predictor residue, ACM Workshop on Multimedia and Security, (2008), 11–20.

25. G. Cao, Y. Zhao and R. Ni, Forensic identification of resampling operators: a semi non-intrusive approach, Foren. Sci. Int., 216 (2012), 29–36.

26. C. Pasquini and R. Bohme, Information-theoretic bounds for the forensic detection of downscaled signals, IEEE T. Inf. Foren. Sec., 14 (2019), 1928–1943.

27. A. C. Gallagher, Detection of linear and cubic interpolation in JPEG compressed images, Canadian Conference on Computer and Robot Vision, (2005), 65–72.

28. L. Nataraj, A. Sarkar and B. Manjunath, Adding gaussian noise to "denoise" JPEG for detecting image resizing, IEEE International Conference on Image Processing, (2009), 1477–1480.

29. M. Kirchner and T. Gloe, On resampling detection in re-compressed images, IEEE International Workshop on Information Forensics and Security, (2009), 21–25.

30. Z. Chen, Y. Zhao and R. Ni, Detection of operation chain: JPEG-resampling-JPEG, Signal Process.-Image, 57 (2017), 8–20.

31. H. Li, W. Luo, X. Qiu, et al., Identification of various image operations using residual-based features, IEEE T. Circ. Syst. Vid., 28 (2018), 31–35.

32. B. Bayar and M. Stamm, On the robustness of constrained convolutional neural networks to JPEG post-compression for image resampling detection, IEEE International Conference on Acoustics, Speech and Signal Processing, (2017), 2152–2156.

33. B. Bayar and M. Stamm, Constrained convolutional neural networks: a new approach towards general purpose image manipulation detection, IEEE T. Inf. Foren. Sec., 13 (2018), 2691–2706.

34. J. Fridrich and J. Kodovsky, Rich models for steganalysis of digital images, IEEE T. Inf. Foren. Sec., 7 (2012), 868–882.

35. Y. Ma, X. Luo, X. Li, et al., Selection of rich model steganalysis features based on decision rough set α-positive region reduction, IEEE T. Circ. Syst. Vid., 29 (2019), 336–350.

36. Y. Zhang, C. Qin, W. Zhang, et al., On the fault-tolerant performance for a class of robust image steganography, Signal Process., 146 (2018), 99–111.

37. X. Luo, X. Song, X. Li, et al., Steganalysis of HUGO steganography based on parameter recognition of syndrome-trellis-codes, Multimed. Tools Appl., 75 (2016), 13557–13583.

38. B. Chen, H. Li and W. Luo, Image processing operations identification via convolutional neural network, preprint, arXiv:1709.02908.

39. I. Sutskever, J. Martens, G. E. Dahl, et al., On the importance of initialization and momentum in deep learning, International Conference on Machine Learning, (2013), 1139–1147.

40. T. Gloe and R. Bohme, The Dresden image database for benchmarking digital image forensics, J. Digit. Foren. Pract., 3 (2010), 1584–1590.

© 2019 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution Licese (http://creativecommons.org/licenses/by/4.0)

Download full text in PDF

Export Citation

Article outline

Show full outline
Copyright © AIMS Press All Rights Reserved