Multimedia Tools and Applications

, Volume 78, Issue 1, pp 489–506 | Cite as

Identifying natural images and computer generated graphics based on binary similarity measures of PRNU

  • Min Long
  • Fei PengEmail author
  • Yin Zhu


Aiming at the identification of natural images and computer generated graphics, an image source pipeline forensics method based on binary similarity measures of PRNU (photo response non-uniformity) is proposed. As PRNU is a unique attribute of natural images, binary similarity measures of PRNU are used to represent the differences between natural images and computer generated graphics. Binary Kullback-Leibler distance, binary minimum histogram distance, binary absolute histogram distance and binary mutual entropy are calculated from PRNU in RGB three channels. With a total of 36 dimensions of features, LIBSVM is used for classification. Experimental results and analysis indicate that it can achieve an average identification accuracy of 99.83%, and the capability of identifying natural images and computer generated graphics is balanced. Meanwhile, it is robust against JPEG compression, rotation and additive noise.


Image source identification Binary similarity measures Photo response non-uniformity noise (PRNU) 



This work was supported in part by project supported by National Natural Science Foundation of China (Grant No. 61572182, 61370225), project supported by Hunan Provincial Natural Science Foundation of China (Grant No.15JJ2007), supported by the Scientific Research Plan of Hunan Provincial Science and Technology Department of China (2014FJ4161).


  1. 1.
    Avcıbaş I, Kharrazi M, Memon N, Sankur B (2015) Image Steganalysis with binary similarity measures, EURASIP. J Adv Appl Signal Process 17:1–9zbMATHGoogle Scholar
  2. 2.
    Bayram S, Avcıbaş I, Sankur B, Memon N, (2005) Image manipulation detection with Binary Similarity Measures. In: Proceedings of 13th European Signal Processing Conference, pp 1–4Google Scholar
  3. 3.
    Chang CC, Lin CJ (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2:389–396CrossRefGoogle Scholar
  4. 4.
    Chang TY, Tai SC, Lin GS (2014) A passive multi-purpose scheme based on periodicity analysis of CFA artifacts for image forensics. J Vis Commun Image Represent 25:1289–1298CrossRefGoogle Scholar
  5. 5.
    Columbia dvmm research lab Columbia photographic images and photorealistic computer generated graphics dataset, [db/dl], (2005–02-05) [2008–08-12]Google Scholar
  6. 6.
    Dresden Image database (2010 3-20), ddimgdb/locations
  7. 7.
    Dubois E (2015) Frequency-domain methods for demosaicking of Bayer-sampled color images. IEEE Signal Process Lett 12:847–850CrossRefGoogle Scholar
  8. 8.
    Fan S, Wang R, Zhang Y, Guo K (2012) Classifying computer generated graphics and natural images based on image contour information. J Inf Comput Sci 9:2877–2895Google Scholar
  9. 9.
    Gao S, Zhang C, Wu CL, et al., (2013) A Hybrid Feature Based Method for Distinguishing Computer Graphics and Photo-Graphic image. In: Proceedings of 12th International Workshop on Digital Forensics and Watermarking, pp.303–313Google Scholar
  10. 10.
    Gao Z, Zhang H, Xu GP, Xue YB, Hauptmannc AG (2015) Multi-view discriminative and structured dictionary learning with group Sparsity for human action recognition. Signal Process 112(C):83–97CrossRefGoogle Scholar
  11. 11.
    Gao Z, Zhang H, Xu GP, Xue YB (2015) Multi-perspective and multi-modality joint representation and recognition model for 3D action recognition. Neurocomputing 151(2):554–564CrossRefGoogle Scholar
  12. 12.
    Haralick RM, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern SMC-3:610–621CrossRefGoogle Scholar
  13. 13.
    Li CT (2010) Source camera identification using enhanced sensor pattern noise. IEEE Trans Inf Forensics Secur 5:280–287CrossRefGoogle Scholar
  14. 14.
    Li Z, Ye J, Shi YQ (2012) Distinguishing computer graphics from photographic images using local binary patterns. In: Proceedings of 11th International Workshop on Digital Forensics and Watermarking, pp. 228–241Google Scholar
  15. 15.
    Li J, Li X, Yang B, Sun X (2015) Segmentation-based Image copy-move forgery detection scheme. IEEE Trans Inf Forensics Secur 10(3):507–518Google Scholar
  16. 16.
    Lian NX, Chang L, Tan YP et al (2007) Adaptive filtering for color filter array demosaicking. IEEE Trans Image Process 16:2515–2525MathSciNetCrossRefGoogle Scholar
  17. 17.
    Liu AA, Su YT, Nie WZ, Kankanhalli M (2016) Hierarchical clustering multi-task learning for joint human action grouping and recognition. IEEE Trans Pattern Anal Mach Intell 39(1):102–114CrossRefGoogle Scholar
  18. 18.
    Liu AA, Nie WZ, Gao Y, Su Y-T (2016) Multi-modal clique-graph matching for view-based 3D model retrieval. IEEE Trans Image Process 25(5):2103–2116MathSciNetCrossRefGoogle Scholar
  19. 19.
    Losson O, Porebski A, Vandenbroucke N et al (2013) Color texture analysis using CFA chromatic co-occurrence matrices. Comput Vis Image Underst 117:747–763CrossRefGoogle Scholar
  20. 20.
    Lv Y, Shen XJ, Wan G, et al. (2014) Blind Identification of Photorealistic Computer Graphics Based on Fractal Dimensions. In: Proceedings of International Conference on Computer, Communications and Information Technology, pp.257–260Google Scholar
  21. 21.
    Lyu S, Farid H (2005) How realistic is photorealistic? IEEE Trans Signal Process 53:845–850MathSciNetCrossRefGoogle Scholar
  22. 22.
    Nie WZ, Liu A.-A, Gao Z, Su Y.-T. (2015) Clique-graph matching by preserving global & local structure. In: Proceeding of the IEEE conference on Computer Vision and Pattern Recognition, pp.4503–4510Google Scholar
  23. 23.
    Nie WZ, Liu A-A, Li WH, Su Y-T (2016) Cross-view action recognition by cross-domain learning. Image Vis Comput 55:109–118CrossRefGoogle Scholar
  24. 24.
    Nie WZ, Liu A-A, Su Y-T (2016) 3D object retrieval based on sparse coding in weak supervision. J Vis Commun Image Represent 37:40–50CrossRefGoogle Scholar
  25. 25.
    Ozparlak L, Avcibas I (2011) Differentiating between images using wavelet-based transforms: a comparative study. IEEE Trans Inf Forensics Secur 6:1418–1431CrossRefGoogle Scholar
  26. 26.
    Peng F, Zhou D (2014) Discriminating natural images and computer generated graphics based on the impact of CFA interpolation on the correlation of PRNU. Digit Investig 11:111–119CrossRefGoogle Scholar
  27. 27.
    Peng F, Li J, Long M (2015) Identification of natural images and computer-generated graphics based on statistical and textural features. J Forensic Sci 60:435–443CrossRefGoogle Scholar
  28. 28.
    Peng F, Zhou D, Long M, Sun X-M (2017) Discrimination of natural images and computer generated graphics based on multi-fractal and regression analysis. AEU Int J Electron Commun 71:72–81CrossRefGoogle Scholar
  29. 29.
    Wang X, Liu Y, Xu B, Li L, Xue J (2014) A statistical feature based approach to distinguish PRCG from photographs. Comput Vis Image Underst 128:84–93CrossRefGoogle Scholar
  30. 30.
    Wang J, Li T, Shi YQ, Lian S, Ye J (2016) Forensics feature analysis in quaternion wavelet domain for distinguishing photographic images and computer graphics. Multimedia Tools and Applications. doi: 10.1007/s11042-016-4153-0
  31. 31.
    Wu R, Li X, Yang B (2011) Identifying computer generated graphics VIA histogram features. In: Proceedings of 18th IEEE International Conference on Image Processing, pp.1933–1936Google Scholar
  32. 32.
    Zhang R, Wang R (2011) Distinguishing photorealistic computer graphics from natural images by imaging features and visual features. In: Proceedings of International Conference on Electronics, Communications and Control. 226–229Google Scholar
  33. 33.
    Zhang H, Zha JJ, Yang Y, Yan S, Gao Y, Chua TS (2013) Attribute-augmented semantic hierarchy: towards bridging semantic gap and intention gap in image retrieval. In Proceedings of the 21st ACM international conference on Multimedia, 33–42Google Scholar
  34. 34.
    Zhang H, Zha ZJ, Yang Y, Yan S, Chua TS (2014) Robust (semi) nonnegative graph embedding. IEEE Trans Image Process 23(7):2996–3012MathSciNetCrossRefGoogle Scholar
  35. 35.
    Zhang H, Shang X, Luan H, Wang M, Chua TS (2016) Learning from collective intelligence: feature learning using social images and tags. ACM Trans Multimed Comput Commun Appl (TOMM) 13(1):1CrossRefGoogle Scholar
  36. 36.
    Zhang H, Shang X, Yang W, Xu H, Luan H, Chua T. S (2016) Online Collaborative Learning for Open-Vocabulary Visual Classifiers. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2809–2817Google Scholar
  37. 37.
    Zhang H, Shen F, Li W, He X, Luan H, Chua TS (2016) Discrete Collaborative Filtering. In: Proceedings of International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, New York, pp 325-334Google Scholar
  38. 38.
    Zhang L, Peng F, Long M (2017) Identifying source camera using guided image estimation and block weighted average. J Vis Commun Image Represent 48:471-479. doi: 10.1016/j.jvcir.2016.12.013
  39. 39.
    Zhou Z, Wang Y. Wang, Wu QMJ, Yang CN, Sun X (2017) Effective and efficient global context verification for image copy detection. IEEE Trans Inf Forensics Secur 12(1):48–63Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2017

Authors and Affiliations

  1. 1.College of Computer and Communication EngineeringChangsha University of Science and TechnologyChangshaPeople’s Republic of China
  2. 2.Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on TransportationChangsha University of Science and TechnologyChangshaChina
  3. 3.College of Computer Science and Electronic EngineeringHunan UniversityChangshaPeople’s Republic of China

Personalised recommendations