Detecting Double Mixed Compressed Images Based on Quaternion Convolutional Neural Network

WANG Hao; WANG Jinwei; HU Xuelong; HU Bingtao; YIN Qilin; LUO Xiangyang; MA Bin; SUN Jinsheng

doi:10.23919/cje.2022.00.179

Article Contents

Article Navigation > Chinese Journal of Electronics > 2024 > Corrected proof

Hao WANG, Jinwei WANG, Xuelong HU, et al., “Detecting Double Mixed Compressed Images Based on Quaternion Convolutional Neural Network,” Chinese Journal of Electronics, vol. 33, no. 3, pp. 1–15, 2024 doi: 10.23919/cje.2022.00.179

Citation:

Hao WANG, Jinwei WANG, Xuelong HU, et al., “Detecting Double Mixed Compressed Images Based on Quaternion Convolutional Neural Network,” Chinese Journal of Electronics, vol. 33, no. 3, pp. 1–15, 2024 doi: 10.23919/cje.2022.00.179

Citation:

PDF( 7532 KB)

Detecting Double Mixed Compressed Images Based on Quaternion Convolutional Neural Network

doi: 10.23919/cje.2022.00.179

WANG Hao^1
,,
WANG Jinwei^{2, 3
,
,},
HU Xuelong^4
,,
HU Bingtao^{2, 3
,},
YIN Qilin^5
,,
LUO Xiangyang^6
,,
MA Bin^7
,,
SUN Jinsheng^1
,

1.
Department of Automation, Nanjing University of Science and Technology, Nanjing 210044, China
2.
Engineering Research Center of Digital Forensics, Ministry of Education, Nanjing 210044, China
3.
Department of Computer and Software, Nanjing University of Information Science and Technology, Nanjing 210044, China
4.
School of Management, Nanjing University of Posts and Telecommunications, Nanjing 210044, China
5.
Department of Computer Science and Engineering, Guangdong Province Key Laboratory of Information Security Technology, Sun Yat-sen University, Guangzhou 510006, China
6.
State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou 450001, China
7.
Shandong Provincial Key Laboratory of Computer Networks and Qilu University of Technology, Jinan 250353, China

More Information

Author Bio:
Hao WANG received his B.S. degree in IoT engineering from Binjiang College, Nanjing University of Information Science & Technology in 2017. He received the M.S. degree in computer science and technology from Computer Science and Software College, Nanjing University of Information Science & Technology in 2020. He is pursuing Ph.D. degree in information security from Nanjing University of Science & Technology. His research interests include multimedia forensics and JPEG compression. (Email: sa875923372@163.com)

Jinwei WANG is a Professor with Nanjing University of Information Science & Technology, Nanjing, China. He received the B.S. degree in automatic control from Inner Mongolia University of Technology in 2000. He received the Ph.D. degree in information security at Nanjing University of Science & Technology in 2007 and was a Visiting Scholar in Service Anticipation Multimedia Innovation (SAMI) Lab of France Telecom R&D Center (Beijing) in 2006. He worked as a Senior Engineer at the 28th research institute, CETC from 2007 to 2010. He worked as a Visiting Scholar at New Jersey Institute of Technology, NJ, USA from 2014 to 2015. His research interests include multimedia copyright protection, multimedia forensics, multimedia encryption and data authentication. He has published more than 50 papers, hosted and participated in more than 10 projects. (Email: wjwei_2004@163.com)

Xuelong HU is an Associate Professor in Nanjing University of Posts and Telecommunications, Nanjing, China. He has been a PI of the National Natural Science Foundation of China and Natural Science Foundation of Jiangsu Provience. His main research fields are systems engineering and quality management. He has published more than 50 papers in some SCI indexed journals. (Email: hxl0419@njupt.edu.cn)

Bingtao HU received the B.S. degree in network engineering from the Nanjing University of Information Science and Technology, Nanjing, China, in 2018. He received the M.S. degree in computer science and technology from Computer Science and Software College, Nanjing University of Information Science & Technology in 2022. His research interests include deep learning and JPEG compression. (Email: 318043256@qq.com)

Qilin YIN received the B.S. degree in network engineering from the Nanjing University of Information Science and Technology, in 2018. He received the M.S. degree in computer science and technology from Computer Science and Software College, Nanjing University of Information Science & Technology in 2021. He is pursuing the Ph.D. degree in information security from Sun Yat-sen University. His research interests include multimedia forensics and deepfake. (Email: qilinyin1995@163.com)

Xiangyang LUO received the B.S., M.S., and Ph.D. degrees from the State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, China, in 2001, 2004, and 2010, respectively. He is the author or co-author of more than 100 refereed international journal and conference papers. He is currently an Associate Professor of the State Key Laboratory of Mathematical Engineering and Advanced Computing. His research interests are image steganography and steganalysis technique. (Email: luoxy_ieu@sina.com)

Bin MA received the M.S. and Ph.D. degrees from Shandong University, Jinan, China, in 2005 and 2008, respectively. From 2008 to 2013, he was an Associate Professor with the School of Information Science, Shandong University of Political Science and Law, Jinan. He visited the New Jersey Institute of Technology at Newark, NJ, USA, as a Visiting Scholar, from 2013 to 2015. He is currently a Professor with the School of Cyber Security, Qilu University of Technology (Shandong Academy of Sciences), Shandong, China. He is also with the Shandong Provincial Key Laboratory of Computer Networks, Jinan. His research interests include reversible data hiding, multimedia security, and image processing. He serves as an Editorial Board Member of a few journals, such as the IEEE Transactions on Information Forensics and Security, the Journal of Visual Communication and Image Representation, and the IEEE Signal Processing. He is a Member of ACM. (Email: sddxmb@126.com)

Jinsheng SUN has been with the School of Automation, NJUST, since 1995, where he is currently a Professor. He received the B.S., M.S. and Ph.D. degrees in control science & engineering from NJUST in 1990, 1992 and 1995. From 2007 to 2009, he visited the University of Melbourne as a Research Fellow at the Department of Electrical and Electronic Engineering. And in 2011, he was with the City University of Hong Kong as a Senior Research Fellow. His research activity includes network congestion control, information security, quality control and distributed control of multi-agent systems. (Email: jssun67@163.com)
Corresponding author: Email: wjwei_2004@163.com
Received Date: 2022-05-27
Accepted Date: 2023-05-23

Available Online: 2023-07-05

Abstract

Abstract

Detection of color images that have undergone double compression is a critical aspect of digital image forensics. Despite the existence of various methods capable of detecting double Joint Photographic Experts Group (JPEG) compression, they are unable to address the issue of mixed double compression resulting from the use of different compression standards. In particular, the implementation of Joint Photographic Experts Group 2000 (JPEG2000) as the secondary compression standard can result in a decline or complete loss of performance in existing methods. To tackle this challenge of JPEG+JPEG2000 compression, a detection method based on quaternion convolutional neural networks (QCNN) is proposed. The QCNN processes the data as a quaternion, transforming the components of a traditional convolutional neural network (CNN) into a quaternion representation. The relationships between the color channels of the image are preserved, and the utilization of color information is optimized. Additionally, the method includes a feature conversion module that converts the extracted features into quaternion statistical features, thereby amplifying the evidence of double compression. Experimental results indicate that the proposed QCNN-based method improves, on average, by 27% compared to existing methods in the detection of JPEG+JPEG2000 compression.
- Color image forensics,
- JPEG,
- JPEG2000,
- Mixed double compression,
- Quaternion convolutional neural network

FullText(HTML)

References(26)

References

[1]	H. Farid, “Seeing is not Believing,” IEEE Spectrum, vol. 46, no. 8, pp. 44–51, 2009. doi: 10.1109/MSPEC.2009.5186556
[2]	A. Rocha, W. Scheirer, T. Boult, et al., “Vision of the unseen: Current trends and challenges in digital image and video forensics,” ACM Computing Surveys, vol. 43, no. 4, article no. articleno.26, 2011. doi: 10.1145/1978802.1978805
[3]	A. Piva, “An overview on image forensics,” International Scholarly Research Notices, vol. 2013, article no. 496701, 2013. doi: 10.1155/2013/496701
[4]	M. C. Stamm, M. Wu, and K. J. R. Liu, “Information forensics: An overview of the first decade,” IEEE Access, vol. 1, pp. 167–200, 2013. doi: 10.1109/ACCESS.2013.2260814
[5]	X. M. Zeng, G. R. Feng, and X. P. Zhang, “Detection of double JPEG compression using modified DenseNet model,” Multimedia Tools and Applications, vol. 78, no. 7, pp. 8183–8196, 2019. doi: 10.1007/s11042-018-6737-3
[6]	J. Lukáš and J. Fridrich, “Estimation of primary quantization matrix in double compressed JPEG images,” in Proceedings Digital Forensic Research Workshop, pp.5–8, 2003.
[7]	F. J. Huang, J. W. Huang, and Y. Q. Shi, “Detecting double JPEG compression with the same quantization matrix,” IEEE Transactions on Information Forensics and Security, vol. 5, no. 4, pp. 848–856, 2010. doi: 10.1109/TIFS.2010.2072921
[8]	J. Q. Yang, J. Xie, G. P. Zhu, et al., “An effective method for detecting double JPEG compression with the same quantization matrix,” IEEE Transactions on Information Forensics and Security, vol. 9, no. 11, pp. 1933–1942, 2014. doi: 10.1109/TIFS.2014.2359368
[9]	Y. K. Niu, X. L. Li, Y. Zhao, et al., “An enhanced approach for detecting double JPEG compression with the same quantization matrix,” Signal Processing:Image Communication, vol. 76, pp. 89–96, 2019. doi: 10.1016/j.image.2019.04.016
[10]	J. W. Wang, H. Wang, J. Li, et al., “Detecting double JPEG compressed color images with the same quantization matrix in spherical coordinates,” IEEE Transactions on Circuits and Systems for Video Technology, vol. vol,30, no. 8, pp. 2736–2749, 2020. doi: 10.1109/TCSVT.2019.2922309
[11]	Y. K. Niu, X. L. Li, Y. Zhao, et al., “Detection of double JPEG compression with the same quantization matrix via convergence analysis,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 32, no. 5, pp. 3279–3290, 2022. doi: 10.1109/TCSVT.2021.3097351
[12]	H. Wang, J. W. Wang, X. Y. Luo, et al., “Detecting aligned double JPEG compressed color image with same quantization matrix based on the stability of image,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 32, no. 6, pp. 4065–4080, 2022. doi: 10.1109/TCSVT.2021.3111195
[13]	Q. Wang and R. Zhang, “Double JPEG compression forensics based on a convolutional neural network,” EURASIP Journal on Information Security, vol. 2016, no. 1, article no. 47, 2016. doi: 10.1186/s13635-016-0047-y
[14]	M. Barni, L. Bondi, N. Bonettini, et al., “Aligned and non-aligned double JPEG detection using convolutional neural networks,” Journal of Visual Communication and Image Representation, vol. 49, pp. 153–163, 2017. doi: 10.1016/j.jvcir.2017.09.003
[15]	B. Li, H. Luo, H. X. Zhang, et al., “A multi-branch convolutional neural network for detecting double JPEG compression,” arXiv preprint, arXiv: 1710.05477, 2017.
[16]	P. Peng, T. F. Sun, X. H. Jiang, et al., “Detection of double JPEG compression with the same quantization matrix based on convolutional neural networks,” in Proceedings of 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, Honolulu, HI, USA, pp.717–721, 2018.
[17]	J. Park, D. Cho, W. Ahn, et al., “Double JPEG detection in mixed JPEG quality factors using deep convolutional neural network,” in Proceedings of the 15th European Conference on Computer Vision, Munich, Germany, pp.636–652, 2018.
[18]	F. M. Liu, Y. H. Wu, and J. X. Yu, “Image compression process and principle of JPEG2000,” Journal of Computer-Aided Design & Computer Graphics, vol. 14, no. 10, pp. 905–911,916, 2002. (in Chinese) doi: 10.3321/j.issn:1003-9775.2002.10.002
[19]	Y. T. Chen, R. L. Xia, K. Zou, et al., “FFTI: Image inpainting algorithm via features fusion and two-steps inpainting,” Journal of Visual Communication and Image Representation, vol. 91, article no. article no. 103776, 2023. doi: 10.1016/j.jvcir.2023.103776
[20]	Y. T. Chen, R. L. Xia, K. Yang, et al., “MFFN: Image super-resolution via multi-level features fusion network,” The Visual Computer, in press.
[21]	D. C. Li, “JPEG2000 image compression standard and applications of key algorithm,” Image Technology, vol. 22, no. 4, pp. 26–31, 2010. (in Chinese) doi: 10.3969/j.issn.1001-0270.2010.04.007
[22]	H. H. Nguyen, T. N. D. Tieu, H. O. Nguyen-Son, et al., “Modular convolutional neural network for discriminating between computer-generated images and photographic images,” in Proceedings of the 13th International Conference on Availability, Reliability and Security, Hamburg, Germany, article no.1, 2018.
[23]	Q. L. Yin, J. W. Wang, X. Y. Luo, et al., “Quaternion convolutional neural network for color image classification and forensics,” IEEE Access, vol. 7, pp. 20293–20301, 2019. doi: 10.1109/ACCESS.2019.2897000
[24]	F. N. Lang, L. Y. Tian, and L. L. Liu, “Quaternion based color face recognition,” Journal of Chengdu University (Natural Science Edition), vol. 32, no. 4, pp. 359–367, 382, 2013. (in Chinese)
[25]	G. Schaefer and M. Stich, “UCID: An uncompressed color image database,” in Proceedings of SPIE 5307, Storage and Retrieval Methods and Applications for Multimedia, San Jose, CA, USA, pp.472–481, 2004.
[26]	NRCS photo gallery. [Online]. Available: http://photogallery.nrcs.usda.gov, 2017-12-07.