Abstract
Passive image forensic techniques investigate fingerprints left by tampering operations. Tampering to a compressed image needs multiple re-compression. Forensic investigation of compressed images involves analysis of quantization fingerprints applied during compression. Re-compressed images show different First Digit Probability Distribution (FDPD) when DCT compression grids of first and later compression are not aligned with each other. Often such images possess fingerprints of first compression. Re-compressed images, having first and re-compression DCT grids aligned with each other, share different FDPD. This paper addresses a technique that uses this divergence in FDPD for locating tampered regions. The divergence in FDPD is used to train the SVM Classifier. Our proposed technique assumes that the tampered region is very small and compression grids will not overlap in that region. Unlike the other techniques, our algorithm does not need pre-computed parameters for training classifiers. Hence, the performance of the SVM classifier is not dependent on the specific compression quality of an image. Algorithm itself evaluates the FDPD model parameters and trains the classifier as per the requirement of the test image.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Mire, A.V., Dhok, S.B., Porey, P.D., Mistry, N.J.: Forensic of digital images using JPEG fingerprint. In: Fifth International IEEE Conference on Signals and Image Processing, Banglore 8–10 January 2014, pp. 131–136. IEEE (2014). https://doi.org/10.1109/ICSIP.2014.26
Bianchi, T., Piva, A.: Image forgery localization via block-grained analysis of JPEG artifacts. IEEE Trans. Inf. Forensics Secur. 7(3) 1003–1017 (2012)
Mire, A.V., Dhok, S.B., Mistry, N.J., Porey, P.D.: Localization of tampering created with Facebook images by analyzing block factor histogram voting. Int. J. Digital Crime Forensics (IJDCF) 7(4), 33–54 (2015)
Fu, D., Shi, Y.Q., Su, W.: A generalized Benford’s law for JPEG coefficients and its applications in image forensics. In: SPIE Conference on Security, Steganography, and Watermarking of Multimedia Contents (2007)
Li, B., Shi, Y.Q., Huang, J.: Detecting doubly compressed JPEG images by using mode based first digit features. In: IEEE International Workshop on Multimedia Signal Pro-cessing (Cairns, Queensland, Australia, 2008), pp. 730–735 (2008)
Li, X.H., Zhao, Y.Q., Liao, M., Shih, F.Y., Shi, Y.Q.: Detection of the tampered region for JPEG images by using mode-based first digit features. EURASIP J. Adv. Signal Process. 2012, 190 (2012)
Mire, A.V., Dhok, S.B., Mistry, N.J., Porey, P.D.: Tampering localization in digital image using first two digit probability features. In: Advances in Intelligent Systems and Computing this link is disabled, 2016, 435, pp. 133–141 (2016)
Benford, F.: The law of anomalous numbers. Proc. Amer. Phil. Soc. 78, 551–572 (1938)
Schaefer, G., Stich, M.: UCID - an uncompressed colour image database. Technical report, School of Computing and Mathematics, Nottingham Trent University, U.K (2003)
Hsu, Y.-F., Chang, S.-F.: Detecting image splicing using geometry invariants and camera characteristics consistency. In: International Conference on Multimedia and Expo (ICME), Toronto, Canada, July 2006. http://www.ee.columbia.edu/ln/dvmm/downloads/authsplcuncmp/
CASIA Tampered Image Detection Evaluation Database. http://forensics.idealtest.org:8080/index_v2.htm. Author, F.: Article title. Journal 2(5), 99–110 (2016)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Mire, A., Malik, S., Jichkar, S. (2022). Tampering Localization Using Divergence in First Digit Probability Distribution. In: Abraham, A., et al. Hybrid Intelligent Systems. HIS 2021. Lecture Notes in Networks and Systems, vol 420. Springer, Cham. https://doi.org/10.1007/978-3-030-96305-7_53
Download citation
DOI: https://doi.org/10.1007/978-3-030-96305-7_53
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-96304-0
Online ISBN: 978-3-030-96305-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)