Skip to main content
SpringerLink
Log in

Discriminative feature projection for camera model identification of recompressed images

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Camera model identification, which aims to identify the source camera model of the query images, has been well studied in the laboratory environment. Most existing methods regard it as a classification problem and rely on well-designed features that characterize the differences between various camera models. In these methods, however, the accuracy of identification results would suffer from the process of image recompression. The information loss reduces the discriminative ability of the designed identification features and results in a serious accuracy loss. To remedy this shortcoming, we investigate the handicap for accurate source identification when the query image is recompressed and creatively propose a new method Discriminative Feature Projection (DFP) to solve this problem. The proposed method learns a discriminative feature projection that projects the designed identification features into a new feature representation invariant to recompression by minimizing the divergence between recompressed and uncompressed images. We also incorporate two constraints that the discrepancy of different images sources should be large and the latent geometric relations of images neighbors should be preserved into our method to reinforce the discriminative ability. Moreover, we conduct extensive experiments over the public Dresden Image Database. Compared with several state-of-the-art methods on camera model identification, the experiment results verify that DFP can achieve significant accuracy promotion when identifying the recompressed images.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

Notes

  1. To prevent any potential confusion, we name the JPEG images directly exported from cameras the original images. The original images are all JPEG images and if they undergo another JPEG compression, we name them recompressed images.

References

  1. Bayram S, Sencar HT, Memon N (2012) Efficient sensor fingerprint matching through fingerprint binarization. IEEE Trans Inf Forensics Secur 7(4):1404–1413

    Article  Google Scholar 

  2. Bayram S, Sencar HT, Memon N (2015) Sensor fingerprint identification through composite fingerprints and group testing. IEEE Trans Inf Forensics Secur 10(3):597–612

    Article  Google Scholar 

  3. Bayram S, Sencar H, Memon N, Avcibas I (2005) Source camera identification based on cfa interpolation. In: Proc IEEE Int Conf Image process, vol 3, Genova, Italy, pp 69–72

  4. Bo W, Guo Y, Kong X, Meng F (2009) Source camera identification forensics based on wavelet features. In: Proc IEEE Fifth Int Conf Intelligent inf. Hiding and multimedia signal process, Kyoto, Japan, pp 702–705

  5. Bo W, Li Y, Sui X, Li M, Guo Y (2019) Joint statistics matching for camera model identification of recompressed images. Math Biosci Eng 16 (5):5041–5061

    Article  MathSciNet  Google Scholar 

  6. Calmon FdP, Wei D, Vinzamuri B, Ramamurthy KN, Varshney KR (2018) Data pre-processing for discrimination prevention: Information-theoretic optimization and analysis. IEEE J Select Topics Signal Process 12(5):1106–1119

    Article  Google Scholar 

  7. Chen M, Fridrich J, Goljan M, Lukás J (2008) Determining image origin and integrity using sensor noise. IEEE Trans Inf Forensics Security 3(1):74–90

    Article  Google Scholar 

  8. Chen C, Stamm MC (2015) Camera model identification framework using an ensemble of demosaicing features. In: Proc IEEE international workshop on information forensics and security (WIFS), pp 1–6

  9. Chierchia G, Parrilli S, Poggi G, Sansone C, Verdoliva L (2010) On the influence of denoising in prnu based forgery detection. In: Proceedings of the 2Nd ACM Workshop on Multimedia in Forensics, Security and Intelligence, MiFor ’10. ACM, New York, pp 117–122

  10. Choi KS, Lam EY, Wong KKY (2006) Source camera identification by jpeg compression statistics for image forensics. In: Proc IEEE Region 10 Conf, Hong Kong, China, pp 1–4

  11. Gao S, Xu G, Hu R-M (2011) Camera model identification based on the characteristic of cfa and interpolation. In: Proc International Workshop on Digital Watermarking (IWDW). Springer, Berlin, pp 268–280

  12. Gloe T (2012) Feature-based forensic camera model identification. Trans Data Hiding and Multimedia Security, pp 42–62

  13. Gloe T, Böhme R (2010) The dresden image database for benchmarking digital image forensics. J Digital Forensic Practice 3(2-4):150–159

    Article  Google Scholar 

  14. Goljan M, Fridrich JJ (2013) Sensor fingerprint digests for fast camera identification from geometrically distorted images. In: Proc SPIE, Burlingame, CA, USA, pp 86650B–86650B10

  15. Gretton A, Borgwardt KM, Rasch M, Schölkopf B, Smola AJ (2007) A kernel method for the two-sample-problem. In: Proc Advances neural inf Process Syst, Vancouver, BC, Canada, pp 513–520

  16. Ho JS, Oscar CA, Zhou J, Guo Y (2010) Inter-channel demosaicking traces for digital image forensics. In: Proc IEEE Int Conf Multimedia expo, Suntec, Singapore, pp 1475–1480

  17. Hou J-U, Lee H-K (2016) Detection of hue modification using photo response nonuniformity. IEEE Trans Circ Syst Video Technol 27(8):1826–1832

    Article  Google Scholar 

  18. Hu Y, Jian C, Li CT (2010) Using improved imaging sensor pattern noise for source camera identification. In: Proc IEEE Int Conf Multimedia expo, Suntec, Singapore, pp 1481–1486

  19. Hu Y, Li CT, Lai Z (2015) Fast source camera identification using matching signs between query and reference fingerprints. Multimedia Tools and Applications 74(18):7405–7428

    Article  Google Scholar 

  20. Hu Y, Li CT, Lin X, Liu B-b (2012) An improved algorithm for camera model identification using inter-channel demosaicking traces. In: 8Th Int Conf Intelligent Inform Hiding and multimedia signal process, Piraeus, Greece, pp 325–330

  21. Kang X, Li Y, Qu Z, Huang F (2012) Enhanced source camera identification performance with a camera reference phase sensor. IEEE Trans Inf Forensics Security 7(2):393–402

    Article  Google Scholar 

  22. Kharrazi M, Sencar HT, Memon N (2004) Blind source camera identification. In: Proc IEEE Int Conf Image Process., Vol 1, Singapore, pp 709–712

  23. Khosravi MR, Samadi S (2019) Data compression in visar sensor networks using non-linear adaptive weighting. EURASIP J Wirel Commun Netw 2019 (1):1–8

    Article  Google Scholar 

  24. Kirchner M, Gloe T (2015) Forensic camera model identification. In: Handbook of digital forensics of multimedia data and devices. Wiley, Chichester, pp 3299–374

  25. Lawgaly A, Khelifi F (2017) Sensor pattern noise estimation based on improved locally adaptive dct filtering and weighted averaging for source camera identification and verification. IEEE Trans Inf Forensics Security 12(2):392–404

    Article  Google Scholar 

  26. Lawgaly A, Khelifi F, Bouridane A (2014) Weighted averaging-based sensor pattern noise estimation for source camera identification. In: Proc IEEE Int Conf Image process, Pari, France, pp 5357–5361

  27. Li CT (2010) Source camera identification using enhanced sensor pattern noise. IEEE Trans Inf Forensics Security 5(2):280–287

    Article  Google Scholar 

  28. Li X, Kong X, Bo W, Guo Y, You X (2013) Generalized transfer component analysis for mismatched jpeg steganalysis. In: Proc IEEE Int Conf ssImage process, Melbourne, VIC, Australia, pp 4432–4436

  29. Li C, Li Y (2012) Color-decoupled photo response non-uniformity for digital image forensics. IEEE Trans Circ Syst Video Technol 22(2):260–271

    Article  MathSciNet  Google Scholar 

  30. Li R, Li CT, Guan Y (2018) Inference of a compact representation of sensor fingerprint for source camera identification. Pattern Recogn 74 ((Supplement C)):556–567

    Article  Google Scholar 

  31. Li Z, Liu J, Tang J, Lu H (2015) Robust structured subspace learning for data representation. IEEE Trans Pattern Anal Mach Intell 37(10):2085–2098

    Article  Google Scholar 

  32. Lin X, Li CT (2016) Enhancing sensor pattern noise via filtering distortion removal. IEEE Signal Process Lett 23(3):381–385

    Article  Google Scholar 

  33. Long M, Wang J, Ding G, Sun J, Yu PS (2013) Transfer feature learning with joint distribution adaptation. In: Proc IEEE Int Conf Comput Vision, San Francisco, CA, USA, pp 2200–2207

  34. Long M, Wang J, Ding G, Sun J, Yu PS (2014) Transfer joint matching for unsupervised domain adaptation. In: Proc IEEE Conf Comput Vision pattern recognit, Columbus, OH, USA, pp 1410–1417

  35. Lukáš J, Fridrich J, Goljan M (2005) Determining digital image origin using sensor imperfections. In: Proc SPIE, San Jose, CA, USA, pp 249–260

  36. Luo L, Wang X, Hu S, Wang C, Tang Y, Chen L (2017) Close yet distinctive domain adaptation. arXiv:1704.04235

  37. Marra F, Poggi G, Sansone C, Verdoliva L (2015) Evaluation of residual-based local features for camera model identification. In: Proc International Conference on Image Analysis and Processing. Springer International Publishing, Genoa, pp 11–18

  38. Marra F, Poggi G, Sansone C, Verdoliva L (2017) A study of co-occurrence based local features for camera model identification. Multimedia Tools and Applications 76(4):4765–4781

    Article  Google Scholar 

  39. Mo, Fridrich JJ, Goljan M (2007) Digital imaging sensor identification (further study). In: Proc SPIE, San Jose, CA, USA, pp 65050P–65050P13

  40. Pan SJ, Tsang IW, Kwok JT, Yang Q (2011) Domain adaptation via transfer component analysis. IEEE Trans Neural Netw 22(2):199–210

    Article  Google Scholar 

  41. Piva A (2013) An overview on image forensics. Isrn Signal Process., 2013(1)

  42. Roy A, Chakraborty RS, Sameer U, Naskar R (2017) Camera source identification using discrete cosine transform residue features and ensemble classifier. In Proc IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops

  43. Stamm MC, Wu M, Liu KJR (2013) Information forensics: an overview of the first decade. IEEE Access 1:167–200

    Article  Google Scholar 

  44. Tang Z, Chen L, Zhang X, Zhang S (2019) Robust image hashing with tensor decomposition. IEEE Trans Knowl Data Eng 31(3):549–560

    Article  Google Scholar 

  45. Tang Z, Zhang X, Li X, Zhang S (2016) Robust image hashing with ring partition and invariant vector distance. IEEE Trans Inform Forensics Security 11(1):200–214

    Article  Google Scholar 

  46. Tomioka Y, Ito Y, Kitazawa H (2013) Robust digital camera identification based on pairwise magnitude relations of clustered sensor pattern noise. IEEE Trans Inf Forensics Security 8(12):1986–1995

    Article  Google Scholar 

  47. Tuama A, Comby F, Chaumont M (2016) Camera model identification based machine learning approach with high order statistics features. In: Proc 24th European signal processing conference (EUSIPCO), pp 1183–1187

  48. Unar S, Wang X, Wang C, Wang M (2019) New strategy for cbir by combining low-level visual features with a colour descriptor. IET Image Process 13:1191–1200

    Article  Google Scholar 

  49. Unar S, Wang X, Wang C, Wang Y (2019) A decisive content based image retrieval approach for feature fusion in visual and textual images. Knowl-Based Syst 179:8–20

    Article  Google Scholar 

  50. Unar Sn, Wang X, Zhang C (2018) Visual and textual information fusion using kernel method for content based image retrieval. Inform Fusion 44:176–187

    Article  Google Scholar 

  51. Unar S, Wang X, Zhang C, Wang C (2019) Detected text-based image retrieval approach for textual images. IET Image Process 13:515–521

    Article  Google Scholar 

  52. Valsesia D, Coluccia G, Bianchi T, Magli E (2015) Compressed fingerprint matching and camera identification via random projections. IEEE Trans Inf Forensics Secur 10(7):1472–1485

    Article  Google Scholar 

  53. Wang X, Chen Z (2009) A fast fractal coding in application of image retrieval. Fractals 17(04):441–450

    Article  MathSciNet  Google Scholar 

  54. Wang X, Chen Z, Yun J (2012) An effective method for color image retrieval based on texture. Computer Standards & Interfaces 34(1):31–35

    Article  Google Scholar 

  55. Wang X, Wang Z (2013) A novel method for image retrieval based on structure elements’ descriptor. J Vis Commun Image Represent 24(1):63–74

    Article  Google Scholar 

  56. Wang X, Wang Z (2014) The method for image retrieval based on multi-factors correlation utilizing block truncation coding. Pattern Recogn 47(10):3293–3303

    Article  Google Scholar 

  57. Wu G, Kang X, Ray Liu KJ (2012) A context adaptive predictor of sensor pattern noise for camera source identification. In: Proc IEEE Int Conf Image process, Orlando, FL, USA, pp 237–240

  58. Xu G, Shi YQ (2012) Camera model identification using local binary patterns. In: Proc IEEE Int Conf Multimedia expo, Melbourne, VIC, Australia

  59. Xu B, Wang X, Zhou X, Xi J, Wang S (2016) Source camera identification from image texture features. Neurocomputing 207:131–140

    Article  Google Scholar 

  60. Zeng L, Kong X, Li M, Guo Y (2015) Jpeg quantization table mismatched steganalysis via robust discriminative feature transformation. In: Proc SPIE Media Watermarking, Security, and Forensics, San Francisco, CA, USA, pp 94090u–94090u9

  61. Zhang G, Bo W, Li Y (2017) Cross-class and inter-class alignment based camera source identification for re-compression images. In: Proc IEEE Int Conf Image graphics, Shanghai, China

Download references

Acknowledgments

This work is supported by the National Natural Science Foundation of China (No. U1936117, No. 62076052, No. 61772111), and the Fundamental Research Funds for the Central Universities (DUT21GF303, DUT20RC(3)088).

Author information

Authors and Affiliations

  1. School of Information and Communication Engineering, Dalian University of Technology, Dalian, People’s Republic of China

    Bo Wang, Yue Wang & Jiayao Hou

  2. Liaoning Normal University, Dalian, Liaoning, 116029, People’s Republic of China

    Xue Sui

  3. Beijing Institute of Electronics Technology and Application, Beijing, 100091, People’s Republic of China

    Meineng Zhu

Authors
  1. Bo Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yue Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jiayao Hou
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Xue Sui
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Meineng Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yue Wang.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, B., Wang, Y., Hou, J. et al. Discriminative feature projection for camera model identification of recompressed images. Multimed Tools Appl 80, 29719–29743 (2021). https://doi.org/10.1007/s11042-021-11201-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-021-11201-7

Keywords

Search

Navigation