Smooth filtering identification based on convolutional neural networks

  • Anan Liu
  • Zhengyu Zhao
  • Chengqian Zhang
  • Yuting Su


The increasing prevalence of digital technology brings great convenience to human life, while also shows us the problems and challenges. Relying on easy-to-use image editing tools, some malicious manipulations, such as image forgery, have already threatened the authenticity of information, especially the electronic evidence in the crimes. As a result, digital forensics attracts more and more attention of researchers. Since some general post-operations, like widely used smooth filtering, can affect the reliability of forensic methods in various ways, it is also significant to detect them. Furthermore, the determination of detailed filtering parameters assists to recover the tampering history of an image. To deal with this problem, we propose a new approach based on convolutional neural networks (CNNs). Through adding a transform layer, obtained distinguishable frequency-domain features are put into a conventional CNN model, to identify the template parameters of various types of spatial smooth filtering operations, such as average, Gaussian and median filtering. Experimental results on a composite database show that putting the images directly into the conventional CNN model without transformation can not work well, and our method achieves better performance than some other applicable related methods, especially in the scenarios of small size and JPEG compression.


Digital forensics Spatial smooth filtering Convolutional neural network Deep learning Discrete Fourier transform JPEG compression 


  1. 1.
    Bahrami K, Kot AC (2015) Image splicing localization based on blur type inconsistency. IEEE Trans Inf Forensics Secur 10(5):999–1009CrossRefGoogle Scholar
  2. 2.
    Bas P, Filler T, Pevný T (2011) Break our steganographic system: The ins and outs of organizing BOSS. In: International Conference on Information Hiding, pp 59–70Google Scholar
  3. 3.
    Cao G, Zhao Y, Ni R, Yu L, Tian H (2010) Forensic detection of median filtering in digital images. In: 2010 IEEE International Conference on Multimedia and expo (ICME), IEEE pp 89–94Google Scholar
  4. 4.
    Chen C, Ni J, Huang J (2013) Blind detection of median filtering in digital images: A difference domain based approach . IEEE Trans Image Process 22:4699–4710MathSciNetCrossRefGoogle Scholar
  5. 5.
    Chen J, Kang X, Liu Y, Wang ZJ (2015) Median filtering forensics based on convolutional neural networks. IEEE Signal Process Lett 22:1849–1853CrossRefGoogle Scholar
  6. 6.
    Chen J, Song X, Nie L, Wang X, Zhang H, Chua TS (2016) Micro tells macro: Predicting the popularity of micro-videos via a transductive model. In: ACM Multimedia Conference, pp 898–907Google Scholar
  7. 7.
    Christlein V, Riess C, Jordan J, Riess C, Angelopoulou E (2012) An evaluation of popular copy-move forgery detection approaches. IEEE Trans Inf Forensics Secur 7(6):1841–1854CrossRefGoogle Scholar
  8. 8.
    Fukushima K (1980) Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol Cybern 36(4):193–202CrossRefMATHGoogle Scholar
  9. 9.
    Gloe T, Bohme R (2010) Dresden image database for benchmarking digital image forensics. In: Proceedings 2010 ACM symp. on appl. computing, Sierre, Switzerland, Mar. 22-26, pp 1584 –1590Google Scholar
  10. 10.
    Glorot X, Bordes A, Bengio Y (2010) Deep sparse rectifier neural networks. J Mach Learn Res 15Google Scholar
  11. 11.
    Gui X, Li X, Qi W, Yang B (2014) Blind median filtering detection based on histogram features. In: Asia-pacific signal and information processing Association, 2014 Annual Summit and Conference (APSIPA), IEEE, pp 1–4Google Scholar
  12. 12.
    Heygster G (1982) Rank filters in digital image processing. Comput Graphics Image Process 19:148–164CrossRefGoogle Scholar
  13. 13.
    Hubel DH, Wiesel TN (1962) Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex. J Physiol 160(1):106–154CrossRefGoogle Scholar
  14. 14.
    Justusson B (1981) Median filtering: Statistical properties. SpringerGoogle Scholar
  15. 15.
    Kang X, Stamm MC, Peng A, Liu KJR (2013) Robust median filtering forensics using an autoregressive model. IEEE Trans Inf Forensics Secur 8:1456–1468CrossRefGoogle Scholar
  16. 16.
    Karayev S, Trentacoste M, Han H, Agarwala A, Darrell T, Hertzmann A, Winnemoeller H (2013) Recognizing image style. Computer ScienceGoogle Scholar
  17. 17.
    Kirchner M, Bohme R (2008) Hiding traces of resampling in digital images. IEEE Trans Inf Forensics Secur 3:582–592CrossRefGoogle Scholar
  18. 18.
    Kirchner M, Fridrich J (2010) On detection of median filtering in digital images. In: Proceedings of SPIE - The International Society for Optical Engineering 7541:1–12Google Scholar
  19. 19.
    Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Proces Syst 25(2):2012Google Scholar
  20. 20.
    Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324CrossRefGoogle Scholar
  21. 21.
    Liu X, Song M, Tao D, Liu Z, Zhang L, Chen C, Bu J (2013) Semi-supervised node splitting for random forest construction. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 492–499Google Scholar
  22. 22.
    Liu Z, Chiew K, He Q, Huang H, Huang B (2014) Prior-free rare category detection: More effective and efficient solutions. Expert Syst Appl Inter J 41(17):7691–7706CrossRefGoogle Scholar
  23. 23.
    Liu Z, Chiew K, Zhang L, Zhang B, He Q, Zimmermann R (2016) Rare category exploration via wavelet analysis: Theory and applications. Expert Syst Appl 63:173–186CrossRefGoogle Scholar
  24. 24.
    Luo W, Huang J, Qiu G (2010) JPEG error analysis and its applications to digital image forensics . IEEE Trans Inf Forensics Secur 5:480–491CrossRefGoogle Scholar
  25. 25.
    Nair V, Hinton GE (2010) Rectified linear units improve restricted boltzmann machines vinod nair. In: International Conference on Machine Learning, pp 807–814Google Scholar
  26. 26.
    Salakhutdinov R, Hinton G (2009) Deep boltzmann machines. J Mach Learn Res 5(2):1967–2006MATHGoogle Scholar
  27. 27.
    Schaefer G, Stich M (2003) UCID: an uncompressed color image database. In: Electronic Imaging 2004, International Society for Optics and Photonics, pp 472–480Google Scholar
  28. 28.
    Scherer D, Müller A, Behnke S (2010) Evaluation of pooling operations in convolutional architectures for object recognition. In: Artificial Neural Networks - ICANN 2010 - International Conference, Thessaloniki, Greece, September 15-18, 2010, Proceedings, pp 92–101Google Scholar
  29. 29.
    Song X, Ming ZY, Nie L, Zhao YL, Chua TS (2016) Volunteerism tendency prediction via harvesting multiple social networks. ACM Trans Inf Syst 34(2)Google Scholar
  30. 30.
    Stamm MC, Liu K (2010) Forensic detection of image manipulation using statistical intrinsic fingerprints. IEEE Trans Inf Forensics Secur 5:492–506CrossRefGoogle Scholar
  31. 31.
    Stamm MC, Liu KJR (2011) Anti-forensics of digital image compression. IEEE Trans Inf Forensics Secur 6:1050–1065CrossRefGoogle Scholar
  32. 32.
    Velleman PF (1980) Definition and comparison of robust nonlinear data smoothing algorithms. J Am Stat Assoc 75:609–615MathSciNetCrossRefMATHGoogle Scholar
  33. 33.
    Vincent P, Larochelle H, Lajoie I, Bengio Y, Manzagol PA (2010) Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. J Mach Learn Res 11(6):3371–3408MathSciNetMATHGoogle Scholar
  34. 34.
    Wang W, Yan Y, Zhang L, Hong R, Sebe N (2016) Collaborative sparse coding for multiview action recognition. IEEE Multimedia Magazine 23(4):80–87CrossRefGoogle Scholar
  35. 35.
    Yuan HD (2011) Blind forensics of median filtering in digital images. IEEE Trans Inf Forensics Secur 6:1335–1345CrossRefGoogle Scholar
  36. 36.
    Zhang L, Han Y, Yang Y, Song M, Yan S, Tian Q (2013a) Discovering discriminative graphlets for aerial image categories recognition. IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society 22(12):5071–5084MathSciNetCrossRefGoogle Scholar
  37. 37.
    Zhang L, Song M, Liu Z, Liu X, Bu J, Chen C (2013b) Probabilistic graphlet cut: Exploiting spatial structure cue for weakly supervised image segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 1908–1915Google Scholar
  38. 38.
    Zhang L, Song M, Zhao Q, Liu X, Bu J, Chen C (2013c) Probabilistic graphlet transfer for photo cropping. IEEE Trans Image Process 22(2):802–15MathSciNetCrossRefGoogle Scholar
  39. 39.
    Zhang L, Gao Y, Hong C, Feng Y, Zhu J, Cai D (2014a) Feature correlation hypergraph: exploiting high-order potentials for multimodal recognition. IEEE Trans Cybernetics 44(8):1408–1419CrossRefGoogle Scholar
  40. 40.
    Zhang L, Gao Y, Ji R, Xia Y, Dai Q, Li X (2014b) Actively learning human gaze shifting paths for semantics-aware photo cropping. IEEE Trans Image Process 23(5):2235–45MathSciNetCrossRefGoogle Scholar
  41. 41.
    Zhang L, Gao Y, Xia Y, Lu K, Shen J, Ji R (2014c) Representative discovery of structure cues for weakly-supervised image segmentation. IEEE Trans Multimedia 16(2):470–479CrossRefGoogle Scholar
  42. 42.
    Zhang L, Yang Y, Gao Y, Yu Y, Wang C, Li X (2014d) A probabilistic associative model for segmenting weakly-supervised images. IEEE Trans Image Process 23(9):4150–4159MathSciNetCrossRefGoogle Scholar
  43. 43.
    Zhang L, Hong R, Gao Y, Ji R, Dai Q, Li X (2015a) Image categorization by learning a propagated graphlet path. IEEE Transactions on Neural Networks and Learning Systems 27(3):674–685MathSciNetCrossRefGoogle Scholar
  44. 44.
    Zhang L, Li X, Nie L, Yan Y, Zimmermann R (2015b) Semantic photo retargeting under noisy image labels. ACM Trans Multimed Comput Commun Appl 12 (3)Google Scholar
  45. 45.
    Zhang L, Wang M, Hong R, Yin BC (2015c) Large-scale aerial image categorization using a multitask topological codebook. IEEE Trans Cybernetics 46(1)Google Scholar
  46. 46.
    Zhang L, Li X, Nie L, Yang Y, Xia Y (2016a) Weakly supervised human fixations prediction. IEEE Trans Cybernetics 46(1):258–269CrossRefGoogle Scholar
  47. 47.
    Zhang L, Yang Y, Wang M, Hong R (2016b) Detecting densely distributed graph patterns for fine-grained image categorization. IEEE Trans Image Process 25 (2):553–565MathSciNetCrossRefGoogle Scholar
  48. 48.
    Zhang N, Paluri M, Ranzato M, Darrell T, Bourdev L (2014e) PANDA: Pose aligned networks for deep attribute modeling. In: Computer Vision and Pattern Recognition, pp 1637–1644Google Scholar
  49. 49.
    Zhang Y, Li S, Wang S, Shi YQ (2014f) Revealing the traces of median filtering using high-order local ternary patterns. IEEE Signal Process Lett 21:275–279CrossRefGoogle Scholar
  50. 50.
    Zhou B, Garcia AL, Xiao J, Torralba A, Oliva A (2014) Learning deep features for scene recognition using places database. Adv Neural Inf Proces Syst 1:487–495Google Scholar

Copyright information

© Springer Science+Business Media New York 2016

Authors and Affiliations

  • Anan Liu
    • 1
  • Zhengyu Zhao
    • 1
  • Chengqian Zhang
    • 2
  • Yuting Su
    • 1
  1. 1.School of Electronic Information EngineeringTianjin UniversityTianjinChina
  2. 2.School of Electrical Engineering and InformationSouthwest Petroleum UniversityChengduChina

Personalised recommendations