Advertisement

An Algorithm for Asymmetric Clipping Detection Based on Parameter Optimization

  • Jiwei Zhang
  • Shaozhang Niu
  • Yueying Li
  • Yuhan Liu
Conference paper
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 82)

Abstract

Asymmetric clipping of digital images is a common method of image tampering, and the existing identification techniques of which are relatively meager. Camera calibration technology is an important method to determine the tampering of asymmetric cutting, but the proposed algorithm has made too many assumptions on the internal parameters matrix of the camera, resulting in some error. This paper presents a parameter optimization algorithm based on camera calibration: by keeping the four parameters in the original camera’s five internal parameters, after approximate processing, to achieve that a single picture contains no coplanar of the two regular geometric figures can calculate the coordinates of the principal point, and as a basis for the image forensics of the asymmetric cutting tampering. The experimental results show that the proposed algorithm can effectively estimate the camera parameters, the application scope and accuracy can be improved greatly, and can accurately detect the image tampering behavior of asymmetric clipping.

Keywords

Blind forensics Regular geometric figures Parameter optimization Camera calibration Asymmetric clipping 

References

  1. 1.
    Bharati, A., Singh, R.: Detecting facial retouching using supervised deep learning. IEEE Trans. Inf. Forensics Secur. 11(9), 1903–1913 (2016)CrossRefGoogle Scholar
  2. 2.
    Ke, Y., Shan, Q., Qin, F., Min, W.: Image recapture detection using multiple features. Int. J. Multimedia Ubiquit. Comput. 8(5), 71–82 (2013)CrossRefGoogle Scholar
  3. 3.
    Ardizzone, E., Bruno, A., Mazzola, G.: Copy-move forgery detection by matching triangles of key points. IEEE Trans. Inf. Forensics Secur. 10(10), 2084–2094 (2015)CrossRefGoogle Scholar
  4. 4.
    El-Alfy, E.S.M., Qureshi, M.A.: Combining spatial and DCT based Markov features for enhanced blind detection of image splicing. Formal Pattern Anal. Appl. 18(3), 1–11 (2014)MathSciNetGoogle Scholar
  5. 5.
    Meng, X., Niu, S.: Technology of digital image tampering based on double JPEG compression. In: National Conference on Information Hiding and Multimedia Information Security (2010)Google Scholar
  6. 6.
    Guo, C., Hong, Y.: Automatic camera calibration method using checkerboard target. J. Comput. Eng. Appl. 52(12), 176–179 (2016)Google Scholar
  7. 7.
    Zhang, Y., Win, L.L., Goh, J., Thing, V.L.L.: image region forgery detection: a deep learning approach. In: Proceedings of the Singapore Cyber-Security Conference (SG-CRC) (2016)Google Scholar
  8. 8.
    Zhang, Z.: A flexible new technique for camera calibration. IEEE Trans. Pattern Anal. Mach. Intell. 22(11), 1330–1334 (2000)CrossRefGoogle Scholar
  9. 9.
    Meng, X., Niu, S.: Asymmetric crop detection algorithm based on camera calibration. J. Electron. Inf. Technol. 34(10) (2012)Google Scholar
  10. 10.
    Johnson, M., Farid, H.: Detecting photographic composites of people. In: 6th International Workshop on Digital Watermarking, Guangzhou, China, vol. 5041, pp. 19–33 (2007)Google Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  1. 1.Beijing Key Lab of Intelligent Telecommunication Software and Multimedia, School of Computer ScienceBeijing University of Posts and TelecommunicationsBeijingChina

Personalised recommendations