A Fast and Efficient Method for Image Splicing Localization Using BM3D Noise Estimation

  • Aswathy M. DasEmail author
  • S. Aji
Part of the Studies in Computational Intelligence book series (SCI, volume 771)


Image manipulation is the process of altering the content of an image with a particular intention or interest. By the developments in the camera industry and powerful editing tools, the image manipulation has become an easy task for even a less skilled person. Therefore, ensuring the authenticity of an image from an external source is necessary before using it. The proposed method deals with detecting an image forgery method known as splicing. It is a comparatively fast and reliable method for image splicing localization. The variation in noise level of different segments, non-overlapped segmentation using simple linear iterative clustering (SLIC), is estimated with the help of Block-Matching and 3D Collaborative Filtering (BM3D). The estimated noise variation is used to cluster the segments where the clusters with relatively higher noise level are located as suspicious or forged regions. It is found that the proposed method takes comparatively less time for execution and the false positive rate is also considerably low. Experimental results show better performance of the proposed method against existing methods of image splicing forgery detection.


Image splicing SLIC BM3D Noise level K-means clustering 


  1. 1.
    Pan, X., X. Zhang, and S. Lyu. 2012. Exposing image splicing with inconsistent local noise variances. In IEEE international conference on computational photography (ICCP), 1–10.Google Scholar
  2. 2.
    Lin, S.D., and T. Wu. 2011. An integrated technique for splicing and copy-move forgery image detection. In 4th international congress on image and signal processing (CISP), 1086–1090.Google Scholar
  3. 3.
    Hsu, Y.F., and S.F. Chang. 2010. Camera response functions for image forensics: An automatic algorithm for splicing detection. IEEE Transactions on Information Forensics and Security 816–825.CrossRefGoogle Scholar
  4. 4.
    Pan, Xunyu, Xing Zhang, and Siwei Lyu. 2012. Exposing image forgery with blind noise estimation. In IEEE international conference on computational photography (ICCP).Google Scholar
  5. 5.
    Lyu, S., X. Pan, and X. Zhang. 2014. Exposing region splicing forgeries with blind local noise estimation. International Journal of Computer Vision 110 (2): 202–221.CrossRefGoogle Scholar
  6. 6.
    Julliand, T., and V. Nozick. 2015. Automated image splicing detection from noise estimation in raw images. In IEEE conference, 1086–1090.Google Scholar
  7. 7.
    Pun, Chi-Man, Bo Liu, and Xiao-Chen Yuan. 2016. Multi-scale noise estimation for image splicing forgery detection. Journal of Visual Communication and Image Representation 195–206.CrossRefGoogle Scholar
  8. 8.
    Dabov, Kostadin. 2007. Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Transactions on Image Processing 2080–2095.MathSciNetCrossRefGoogle Scholar
  9. 9.
    Achanta, R., A. Shaji, K. Smith, A. Lucch, and S. Susstrunk. 2012. SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Transactions on Pattern Analysis and Machine Intelligence 2274–82.CrossRefGoogle Scholar
  10. 10.
    Kanungo, T., and D.M. Mount. 2002. An efficient k-means clustering algorithm: Analysis and implementation. IEEE Transactions on Pattern Analysis and Machine Intelligence.Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Department of Computer ScienceUniversity of KeralaThiruvananthapuramIndia

Personalised recommendations