ABSTRACT
We address the known problem of detecting a previous compression in JPEG images, focusing on the challenging case of high and very high quality factors (>= 90) as well as repeated compression with identical or nearly identical quality factors. We first revisit the approaches based on Benford--Fourier analysis in the DCT domain and block convergence analysis in the spatial domain. Both were originally conceived for specific scenarios. Leveraging decision tree theory, we design a combined approach complementing the discriminatory capabilities. We obtain a set of novel detectors targeted to high quality grayscale JPEG images.
- T. Bianchi, A. Piva, and F. Pérez-González. Near optimal detection of quantized signals and application to JPEG forensics. In IEEE Workshop on Informations Forensics and Security (WIFS), 2013.Google ScholarCross Ref
- L. Breslow and D. Aha. Simplifying decision trees: A survey. The Knowledge Engineering Review, 12(1):1--40, 1997. Google ScholarDigital Library
- M. Carnein, P. Schöttle, and R. Böhme. Forensics of high-quality JPEG images with color subsampling. In IEEE Workshop on Informations Forensics and Security (WIFS), 2015.Google ScholarCross Ref
- Y. Chen and C. Hsu. Detecting recompression of JPEG images via periodicity analysis of compression artifacts for tampering detection. IEEE Transactions on Information Forensics and Security, 6, n. 2:396--406, 2011. Google ScholarDigital Library
- T. Gloe and R. Boehme. The Dresden image database for benchmarking digital image forensics. In ACM Symposium on Applied Computing, volume 2, pages 1585--1591, 2010. Google ScholarDigital Library
- F. Huang, J. Huang, and Y. Shi. Detecting double JPEG compression with the same quantization matrix. IEEE Transactions on Information Forensics and Security, 5(4):848--856, 2010. Google ScholarDigital Library
- S.-Y. Lai and R. Böhme. Block convergence in repeated transform coding: JPEG-100 forensics, carbon dating, and tamper detection. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 3028--3032, 2013.Google ScholarCross Ref
- B. Li, Y. Shi, and J. Huang. Detecting doubly compressed JPEG images by using mode based first digit features. In IEEE Workshop on Multimedia Signal Processing (MMSP), pages 730--735, 2008.Google Scholar
- S. Milani, M. Tagliasacchi, and S. Tubaro. Discriminating multiple JPEG compression using first digit features. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 25--30, 2012.Google ScholarCross Ref
- C. Pasquini, G. Boato, and F. Pérez-González. Multiple JPEG compression detection by means of Benford-Fourier coefficients. In IEEE Workshop on Informations Forensics and Security (WIFS), pages 113--118, 2014.Google ScholarCross Ref
- C. Pasquini, F. Pérez-González, and G. Boato. A Benford-Fourier JPEG compression detector. In IEEE International Conference on Image Processing (ICIP), pages 5322--5326, 2014.Google ScholarCross Ref
- F. Pérez-González, T. Quach, S. J. Miller, C. Abdallah, and G. Heileman. Application of Benford's law to images. S. J. Miller, A. Berger and T. Hill (Eds), The Theory and Applications of Benford's law, Princeton University Press, 2015.Google Scholar
- T. Pevnỳ and J. Fridrich. Detection of double-compression in JPEG images for applications in steganography. IEEE Transactions on Information Forensics and Security, 3(2):247--258, 2008. Google ScholarDigital Library
- L. Rokach and O. Maimon. Top-down induction of decision trees classifiers - a survey. IEEE Transactions on Systems, Man, and Cybernetics, 35(4):476--487, 2005. Google ScholarDigital Library
- G. Schaefer and M. Stich. UCID - An uncompressed colour image database. In SPIE Storage and Retrieval Methods and Applications to Multimedia, volume 5307, 2004.Google Scholar
- J. Yang, J. Xie, G. Zhu, S. Kwong, and Y. Shi. An effective method for detecting double JPEG compression with the same quantization matrix. IEEE Transactions on Information Forensics and Security, 9(11), 2014. Google ScholarDigital Library
Index Terms
- Forensics of High Quality and Nearly Identical JPEG Image Recompression
Recommendations
Image Forensics from Chroma Subsampling of High-Quality JPEG Images
IH&MMSec'19: Proceedings of the ACM Workshop on Information Hiding and Multimedia SecurityThe JPEG compression format provides a rich source of forensic traces that include quantization artifacts, fingerprints of the container format, and numerical particularities of JPEG compressors. Such a diverse set of cues serves as the basis for a ...
Improving image quality for JPEG compression
KES'05: Proceedings of the 9th international conference on Knowledge-Based Intelligent Information and Engineering Systems - Volume Part IIIJPEG is a well-known method for digital image compression. The drawback of JPEG is distortion to image quality by truncation errors from quantizing the DCT coefficients. Another problem is the damage on the extracted watermarks from JPEG compression for ...
JPEG error analysis and its applications to digital image forensics
JPEG is one of the most extensively used image formats. Understanding the inherent characteristics of JPEG may play a useful role in digital image forensics. In this paper, we introduce JPEG error analysis to the study of image forensics. The main ...
Comments