Image Splicing Detection Based on Improved Markov Model

  • Su Bo
  • Yuan Quan-qiao
  • Wang Shi-lin
  • Zhao Cheng-lin
  • Li Shen-ghong
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 246)


Digital image splicing detection is a new and important subject in image forensics. Research shows that Discrete Cosine Transform (DCT) and Discrete Wavelet Transform (DWT) based Markov features are effective for image splicing detection. However, the state selection in the traditional Markov model was simply rounding the parameters and taking threshold value, which has not exploited the parameter distribute information. In this paper, a novel Markov state selection method is proposed. The approach matches states with parameters evenly according to fixed ratio calculated by pre-set state numbers. Experiments show that the improved Markov model achieves higher recognition accuracy rate compared with the traditional Markov model with the same feature dimension.


DCT DWT Markov model State selection Image splicing detection 



This work is funded by National Science Foundation of China (61271316, 61071152), 973 Program (2010CB731403, 2010CB731406, 2013CB329605) of China, Chinese National “Twelfth Five-Year” Plan for Science & Technology Support (2012BAH38 B04), Key Laboratory for Shanghai Integrated Information Security Management Technology Research, and Chinese National Engineering Laboratory for Information Content Analysis Technology.


  1. 1.
    Nikolaidis N, Pitas I (1996) Copyright protection of images using robust digital signatures. In: Reeves SJ (ed) Proceeding on international conference on acoustics, speech, and signal processing. IEEE Press, Atlanta, GA, pp 216–217Google Scholar
  2. 2.
    Cox IJ, Kilian J, Leighton FT et al (1997) Secure spread spectrum watermarking for multimedia. IEEE Trans Image Process 6(12):1673–1687CrossRefGoogle Scholar
  3. 3.
    Farid H (2009) A survey of image forgery detection. IEEE Signal Process Mag 26(2):16–25CrossRefGoogle Scholar
  4. 4.
    Shi YQ, Chen C, Chen W (2007) A natural image model approach to splicing detection. In: Deepa K, Balakrishnan P (eds) 9th workshop on multimedia and security. ACM, New York, NY, pp 51–62Google Scholar
  5. 5.
    Columbia DVMM Research Lab (2004) Columbia image splicing detection evaluation dataset,
  6. 6.
    Chen W, Shi, Y (2007) Image splicing detection using 2D phase congruency and statistical moments of characteristic function, In: Proc. SPIE, electronic imaging, security, steganography, watermarking of multimedia contents IX, San Jose, CA, 29 January–1 February, 2007, vol. 6505, pp. 0R–0SGoogle Scholar
  7. 7.
    Dong J, Wang W, Tan T, Shi Y (2008) Run-length and edge statistics based approach for image splicing detection. In: Digital watermarking, 7th international workshop, IWDW 2008, Busan, Korea, 10–12 November, 2008, pp. 76–87Google Scholar
  8. 8.
    Xudong Zhao, Jianhua Li, Shenghong Li and Shilin Wang (2010) Detecting digital image splicing in chroma spaces. International workshop on digital watermarking, Seoul, Korea, 1–3 October, 2010, LNCS, vol. 6526, pp. 12–22Google Scholar
  9. 9.
    He Z, Lu W, Sun W et al (2012) Digital image splicing detection based on Markov features in DCT and DWT domain. Pattern Recogn 45(12):4292–4299CrossRefGoogle Scholar
  10. 10.
    Chang C-C, Lin C-J (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2(27):1–27. Software available at

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Su Bo
    • 1
  • Yuan Quan-qiao
    • 1
  • Wang Shi-lin
    • 1
  • Zhao Cheng-lin
    • 2
  • Li Shen-ghong
    • 1
  1. 1.School of electronic information and electrical engineeringShanghai Jiao Tong UniversityShanghai CityChina
  2. 2.Information and Communication EngineeringBeijing University of Posts and TelecommunicationsBeijing CityChina

Personalised recommendations