Multimedia Tools and Applications

, Volume 76, Issue 6, pp 7749–7783 | Cite as

A novel forensic image analysis tool for discovering double JPEG compression clues

  • Ali Taimori
  • Farbod Razzazi
  • Alireza Behrad
  • Ali Ahmadi
  • Massoud Babaie-Zadeh
Article

Abstract

This paper presents a novel technique to discover double JPEG compression traces. Existing detectors only operate in a scenario that the image under investigation is explicitly available in JPEG format. Consequently, if quantization information of JPEG files is unknown, their performance dramatically degrades. Our method addresses both forensic scenarios which results in a fresh perceptual detection pipeline. We suggest a dimensionality reduction algorithm to visualize behaviors of a big database including various single and double compressed images. Based on intuitions of visualization, three bottom-up, top-down and combined top-down/bottom-up learning strategies are proposed. Our tool discriminates single compressed images from double counterparts, estimates the first quantization in double compression, and localizes tampered regions in a forgery examination. Extensive experiments on three databases demonstrate results are robust among different quality levels. F1-measure improvement to the best state-of-the-art approach reaches up to 26.32 %. An implementation of algorithms is available upon request to fellows.

Keywords

Compressive sensing Dimensionality reduction Double compression detection Forgery locating Recompression history identification Top-down and bottom-up processing 

References

  1. 1.
    Baudat G, Anouar F (2000) Generalized discriminant analysis using a kernel approach. Neural Comput 12(10):2385–2404CrossRefGoogle Scholar
  2. 2.
    Berger A, Hill TP (2011) A basic theory of Benford’s law. Probab Surv 8:1–126MathSciNetCrossRefMATHGoogle Scholar
  3. 3.
    Bianchi T, Piva A (2012) Image forgery localization via block-grained analysis of JPEG artifacts. IEEE Trans Inf Forensics Secur 7(3):1003–1017CrossRefGoogle Scholar
  4. 4.
    Borenstein E, Ullman S (2008) Combined top-down/bottom-up segmentation. IEEE Trans Pattern Anal Mach Intell 30(12):2109–2125CrossRefGoogle Scholar
  5. 5.
    Chang CC, Lin CJ (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol (TIST) 2(3). article 27Google Scholar
  6. 6.
    Cheng H, Liu Z, Yang L, Chen X (2013) Sparse representation and learning in visual recognition: theory and applications. Signal Process 93(6):1408–1425CrossRefGoogle Scholar
  7. 7.
    Dong L, Kong X, Wang B, You X (2011) Double compression detection based on Markov model of the first digits of DCT coefficients. In: IEEE 6Th international conference on image and graphics (ICIG), pp 234–237Google Scholar
  8. 8.
    Duarte MF, Eldar YC (2011) Structured compressed sensing: from theory to applications. IEEE Trans Signal Process 59(9):4053–4085MathSciNetCrossRefGoogle Scholar
  9. 9.
    Evans N, Bozonnet S, Wang D, Fredouille C, Troncy R (2012) A comparative study of bottom-up and top-down approaches to speaker diarization. IEEE Trans Audio Speech Lang Process 20(2):382–392CrossRefGoogle Scholar
  10. 10.
    Farid H (2006) Digital image ballistics from JPEG quantization. Tech. Rep. TR2006-583, Department of Computer Science Dartmouth CollegeGoogle Scholar
  11. 11.
    Farid H (2009) Image forgery detection. IEEE Signal Proc Mag 26(2):16–25CrossRefGoogle Scholar
  12. 12.
    Galvan F, Puglisi G, Bruna A, Battiato S (2014) First quantization matrix estimation from double compressed JPEG images. IEEE Trans Inf Forensics Secur 9 (8):1299–1310CrossRefGoogle Scholar
  13. 13.
    Gao J, Shi Q, Caetano TS (2012) Dimensionality reduction via compressive sensing. Pattern Recogn Lett 33(9):1163–1170CrossRefGoogle Scholar
  14. 14.
    He H, Garcia EA (2009) Learning from imbalanced data. IEEE Trans Knowl Data Eng 21(9):1263–1284CrossRefGoogle Scholar
  15. 15.
    Jolliffe IT (2002) Principal component analysis. Springer Series in Statistics The 2nd editionGoogle Scholar
  16. 16.
    Kaski S, Peltonen J (2011) Dimensionality reduction for data visualization. IEEE Signal Proc Mag 28(2):100–104CrossRefGoogle Scholar
  17. 17.
    Levin A, Weiss Y (2009) Learning to combine bottom-up and top-down segmentation. Int J Comput Vis 81(1):105–118CrossRefGoogle Scholar
  18. 18.
    Li B, Shi YQ, Huang J (2008) Detecting doubly compressed JPEG images by using mode based first digit features. In: IEEE 10Th workshop on multimedia signal processing, pp 730–735Google Scholar
  19. 19.
    Li XH, Zhao YQ, Liao M, Shih FY, Shi YQ (2012) Detection of tampered region for JPEG images by using mode-based first digit features. EURASIP Journal on Advances in Signal Processing 1–10Google Scholar
  20. 20.
    Lin HT, Lin CJ, Weng RC (2007) A note on Platt’s probabilistic outputs for support vector machines. Mach Learn 68(3):267–276CrossRefGoogle Scholar
  21. 21.
    Lin WS, Tjoa SK, Zhao HV, Liu KR (2009) Digital image source coder forensics via intrinsic fingerprints. IEEE Trans Inf Forensics Secur 4(3):460–475CrossRefGoogle Scholar
  22. 22.
    Lin Z, He J, Tang X, Tang CK (2009) Fast, automatic and fine-grained tampered JPEG image detection via DCT coefficient analysis. Pattern Recogn 42(11):2492–2501CrossRefMATHGoogle Scholar
  23. 23.
    Liu J, Ji S, Ye J (2011) SLEP: sparse learning with efficient projections Arizona State University 2011Google Scholar
  24. 24.
    Liu Q, Sung AH, Qiao M (2011) A method to detect JPEG-based double compression. In: The 8th international conference on advances in neural networks, lecture notes in computer science, Part II, pp 466–476Google Scholar
  25. 25.
    Liu Q, Sung AH, Qiao M (2011) Neighboring joint density-based JPEG steganalysis. ACM Trans Intell Syst Technol (TIST) 2(2). article 16Google Scholar
  26. 26.
    Lukáš J, Fridrich J (2003) Estimation of primary quantization matrix in double compressed JPEG images. In: Proc. Digital forensic research workshopGoogle Scholar
  27. 27.
    van der Maaten L (2009) Learning a parametric embedding by preserving local structure. In: International conference on artificial intelligence and statistics, pp 384–391Google Scholar
  28. 28.
    van der Maaten L, Hinton G (2008) Visualizing data using SNE. J Mach Learn Res 9:2579–2605MATHGoogle Scholar
  29. 29.
    van der Maaten L, Postma EO, van den Herik HJ (2009) Dimensionality reduction: a comparative review. Tech. Rep. tiCC-TR 2009-005, Tilburg Centre for Creative Computing Tilburg UniversityGoogle Scholar
  30. 30.
    Mahalakshmi SD, Vijayalakshmi K, Priyadharsini S (2012) Digital image forgery detection and estimation by exploring basic image manipulations. Digit Investig 8(3):215–225CrossRefGoogle Scholar
  31. 31.
    Milani S, Tagliasacchi M, Tubaro S (2012) Discriminating multiple JPEG compression using first digit features. In: IEEE International conference on acoustics, speech and signal processing (ICASSP), pp 2253–2256Google Scholar
  32. 32.
    Olmos A, Kingdom FAA (2004) A biologically inspired algorithm for the recovery of shading and reflectance images. Perception 33(12):1463–1473CrossRefGoogle Scholar
  33. 33.
    Pearson K (1901) On lines and planes of closest fit to systems of points in space. Phil Mag 2(11):559–572CrossRefMATHGoogle Scholar
  34. 34.
    Peng Y, Liu B (2013) Accurate estimation of primary quantisation table with applications to tampering detection. Electron Lett 49(23):1452–1454CrossRefGoogle Scholar
  35. 35.
    Piva A (2013) An overview on image forensics. ISRN Signal Processing p article ID 496701Google Scholar
  36. 36.
    Redi JA, Taktak W, Dugelay JL (2011) Digital image forensics: a booklet for beginners. Multimedia Tools Appl 51(1):133–162CrossRefGoogle Scholar
  37. 37.
    Sencar HT, Memon N (2009) Identification and recovery of JPEG files with missing fragments. Digit Investig 6:S88–S98CrossRefGoogle Scholar
  38. 38.
    Silverman BW (1986) Density estimation for statistics and data analysis. Monogr Stat Appl Probab 26:1–22MATHGoogle Scholar
  39. 39.
    Soille P (2004) Morphological image analysis: principles and applications. Springer-verlag New York, Inc. The 2nd editionGoogle Scholar
  40. 40.
    Taimori A, Behrad A (2015) A new deformable mesh model for face tracking using edge based features and novel sets of energy functions. Multimedia Tools Appl 74(23):10,735–10,759CrossRefGoogle Scholar
  41. 41.
    Taimori A, Razzazi F, Behrad A, Ahmadi A, Babaie-Zadeh M (2012) A proper transform for satisfying Benford’s law and its application to double JPEG image forensics. In: IEEE International symposium on signal processing and information technology (ISSPIT), pp. 000,240–000,244Google Scholar
  42. 42.
    Taimori A, Razzazi F, Behrad A, Ahmadi A, Babaie-Zadeh M (2015) Quantization-unaware double JPEG compression detection. Journal of Mathematical Imaging and Vision. doi:10.1007/s10851-015-0602-z
  43. 43.
    Tian H, Fang Y, Yao Z, Lin W, Ni R, Zhu Z (2014) Salient region detection by fusing bottom-up and top-down features extracted from a single image. IEEE Trans Image Process 23(10):4389–4398MathSciNetCrossRefGoogle Scholar
  44. 44.
    Ulusoy I, Bishop CM (2005) Generative versus discriminative methods for object recognition. In: IEEE Computer society conference on computer vision and pattern recognition (CVPR), vol 2, pp 258–265Google Scholar
  45. 45.
    Wallace GK (1992) The JPEG still picture compression standard. IEEE Trans Consum Electron 38(1):xviii–xxxivCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2016

Authors and Affiliations

  • Ali Taimori
    • 1
  • Farbod Razzazi
    • 2
  • Alireza Behrad
    • 3
  • Ali Ahmadi
    • 4
  • Massoud Babaie-Zadeh
    • 5
  1. 1.Young Researchers and Elite ClubParand Branch, Islamic Azad UniversityParandIran
  2. 2.Department of Electrical and Computer EngineeringScience and Research Branch, Islamic Azad UniversityTehranIran
  3. 3.Faculty of EngineeringShahed UniversityTehranIran
  4. 4.Department of Electrical and Computer EngineeringK. N. Toosi University of TechnologyTehranIran
  5. 5.Department of Electrical EngineeringSharif University of TechnologyTehranIran

Personalised recommendations