Abstract
Double JPEG compression is the most common process to hide image manipulation. Therefore, it becomes necessary to detect the double JPEG compression. Several approaches have been developed for double JPEG compression detection with high accuracy, but they do not provide a unified solution in terms of real-time applicability. To address this issue, a new 953-dimensional unified detector is proposed. The unified detector is a combination of 44 spatial domain features and 909 frequency domain features. Extensive experiments are performed on UCID and RAISE databases to evaluate the robustness of the proposed detector. In addition, the proposed detector is evaluated and compared with a state-of-the-art method under a multi-class (9-class) classification.
Similar content being viewed by others
References
Amerini, I., Uricchio, T., Ballan, L., Caldelli, R.: Localization of jpeg double compression through multi-domain convolutional neural networks. pp. 1865–1871 (2017). https://doi.org/10.1109/CVPRW.2017.233
Barni, M., Bondi, L., Bonettini, N., Bestagini, P., Costanzo, A., Maggini, M., Tondi, B., Tubaro, S.: Aligned and non-aligned double jpeg detection using convolutional neural networks. J. Vis. Commun. Image Represent. 49 (2017). https://doi.org/10.1016/j.jvcir.2017.09.003
Bas, P., Filler, T., Pevný, T.: Break our steganographic system: the ins and outs of organizing boss. In: Filler, T., Pevný, T., Craver, S., Ker, A. (eds.) Inform. Hiding, pp. 59–70. Springer, Berlin Heidelberg (2011)
Bianchi, T., Piva, A.: Detection of nonaligned double jpeg compression based on integer periodicity maps. IEEE Trans. Inform. Foren. Secur. 7(2), 842–848 (2012). https://doi.org/10.1109/TIFS.2011.2170836
Cao, G., Zhao, Y., Ni, R., Li, X.: Contrast enhancement-based forensics in digital images. IEEE Trans. Inform. Foren. Secur. 9, 515–525 (2014). https://doi.org/10.1109/TIFS.2014.2300937
Chen, T., Guestrin, C.: Xgboost. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2016). https://doi.org/10.1145/2939672.2939785
Chen, Y.L., Hsu, C.T.: Detecting recompression of jpeg images via periodicity analysis of compression artifacts for tampering detection. IEEE Trans. Inform. Foren. Secur. 6, 396–406 (2011). https://doi.org/10.1109/TIFS.2011.2106121
Dang-Nguyen, D.T., Pasquini, C., Conotter, V., Boato, G.: Raise: A raw images dataset for digital image forensics. In: Proceedings of the 6th ACM Multimedia Systems Conference, MMSys ’15, pp. 219–224. ACM, New York, NY, USA (2015). https://doi.org/10.1145/2713168.2713194
Diallo, B., Urruty, T., Bourdon, P., Fernandez-Maloigne, C.: Robust forgery detection for compressed images using cnn supervision. Foren. Sci. Int. Rep. 2, 100112 (2020). https://doi.org/10.1016/j.fsir.2020.100112
Doane, D.P.: Aesthetic frequency classifications. Am. Stat. JSTOR 30(4), 181–183 (1976). https://doi.org/10.2307/2683757
Fontani, M., Barni, M.: Hiding traces of median filtering in digital images. pp. 1239–1243 (2012)
Harish, A., Verma, V., Khanna, N.: Double jpeg compression detection for distinguishable blocks in images compressed with same quantization matrix. pp. 1–6 (2020). https://doi.org/10.1109/MLSP49062.2020.9231749
Hussain, I., Tan, S., Li, B., Qin, X., Hussain, D., Huang, J.: A novel deep learning framework for double jpeg compression detection of small size blocks. J. Vis. Commun. Image Represent. 80, 103269 (2021). https://doi.org/10.1016/j.jvcir.2021.103269
Kang, X., Stamm, M., Anjie, P., Liu, K.J.R.: Robust median filtering forensics based on the autoregressive model of median filtered residual. pp. 1–9 (2012)
Kim, D., Ahn, W., Lee, H.K.: End-to-end anti-forensics network of single and double jpeg detection. IEEE Access 9, 13390–13402 (2021). https://doi.org/10.1109/ACCESS.2021.3051678
Kirchner, M., Fridrich, J.: On detection of median filtering in digital images. p. 754110 (2010). https://doi.org/10.1117/12.839100
Korus, P., Huang, J.: Multi-scale fusion for improved localization of malicious tampering in digital images. IEEE Trans. Image Process. 25(3), 1312–1326 (2016). https://doi.org/10.1109/TIP.2016.2518870
Li, B., Shi, Y.Q., Huang, J.: Detecting doubly compressed jpeg images by using mode based first digit features. In: 2008 IEEE 10th Workshop on Multimedia Signal Processing, pp. 730–735 (2008). https://doi.org/10.1109/MMSP.2008.4665171
Li, B., Luo, H., Zhang, H., Tan, S., Ji, Z.: A multi-branch convolutional neural network for detecting double jpeg compression (2017)
Li, B., Zhang, H., Luo, H., Tan, S.: Detecting double jpeg compression and its related anti-forensic operations with cnn. Multimed. Tools Appli. 78 (2019). https://doi.org/10.1007/s11042-018-7073-3
Lukáš, J., Fridrich, J.: Estimation of primary quantization matrix in double compressed jpeg images. In: Proc. Digital Forensic Research Workshop, pp. 5–8 (2003)
Mittal, A., Moorthy, A., Bovik, A.: No-reference image quality assessment in the spatial domain. In: IEEE transactions on image processing : a publication of the IEEE Signal Processing Society 21 (2012). https://doi.org/10.1109/TIP.2012.2214050
Niu, Y., Li, X., Zhao, Y., Ni, R.: Detection of double jpeg compression with the same quantization matrix via convergence analysis. IEEE Transactions on Circuits and Systems for Video Technology pp. 1–1 (2021). https://doi.org/10.1109/TCSVT.2021.3097351
Pevny, T., Fridrich, J.: Detection of double-compression in jpeg images for applications in steganography. IEEE Trans. Inform. Foren. Secur. 3(2), 247–258 (2008). https://doi.org/10.1109/TIFS.2008.922456
Popescu, A.C., Farid, H.: Statistical tools for digital forensics. In: In 6th International Workshop on Information Hiding, pp. 128–147. Springer, Berlin-Heidelberg (2004)
Roenko, A., Lukin, V., Djurovic, I., Simeunović, M.: Estimation of parameters for generalized gaussian distribution. pp. 376–379 (2014). https://doi.org/10.1109/ISCCSP.2014.6877892
Schaefer, G., Stich, M.: UCID: an uncompressed color image database. In: M.M. Yeung, R.W. Lienhart, C.S. Li (eds) Storage and Retrieval Methods and Applications for Multimedia 2004, vol. 5307, pp. 472 – 480. International Society for Optics and Photonics, SPIE (2003). https://doi.org/10.1117/12.525375
Tesei, A., Regazzoni, C.: The asymmetric generalized gaussian function: a new hos-based model for generic noise pdfs. In: Proceedings of 8th Workshop on Statistical Signal and Array Processing, pp. 210–213 (1996). https://doi.org/10.1109/SSAP.1996.534855
Verma, V., Agarwal, N., Khanna, N.: Dct-domain deep convolutional neural networks for multiple jpeg compression classification. Signal Process. Image Commun. 67 (2017). https://doi.org/10.1016/j.image.2018.04.014
Wang, Q., Zhang, R.: Double jpeg compression forensics based on a convolutional neural network. EURASIP J. Inform. Secur. 2016 (2016). https://doi.org/10.1186/s13635-016-0047-y
Wang, J., Huang, W., Luo, X., Shi, Y., Jha, S.: Non-aligned double jpeg compression detection based on refined markov features in qdct domain. J. Real-Time Image Process. 17 (2020). https://doi.org/10.1007/s11554-019-00929-z
Wang, J., Wang, H., Li, J., Luo, X., Shi, Y.Q., Jha, S.K.: Detecting double jpeg compressed color images with the same quantization matrix in spherical coordinates. IEEE Trans. Circ. Syst. Video Technol. 30(8), 2736–2749 (2020). https://doi.org/10.1109/TCSVT.2019.2922309
Wen, L., Qi, H., Lyu, S.: Contrast enhancement estimation for digital image forensics. ACM Trans. Multimed. Comput. Commun. Appl. 14 (2017). https://doi.org/10.1145/3183518
Funding
The authors have no relevant financial or non-financial interests to disclose.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Agarwal, A., Gupta, A. Real-time double JPEG forensics for mobile devices. J Real-Time Image Proc 19, 727–737 (2022). https://doi.org/10.1007/s11554-022-01218-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11554-022-01218-y