Spatial Domain-Based Nonlinear Residual Feature Extraction for Identification of Image Operations
Source abstract
Abstract
In this paper, a novel approach that uses a deep learning technique is proposed to detect and identify a variety of image operations. First, we propose the spatial domain-based nonlinear residual (SDNR) feature extraction method by constructing residual values from locally supported filters in the spatial domain. By applying minimum and maximum operators, diversity and nonlinearity are introduced; moreover, this construction brings nonsymmetry to the distribution of SDNR samples. Then, we propose applying a deep learning technique to the extracted SDNR features to detect and classify a variety of image operations. Many experiments have been conducted to verify the performance of the proposed approach, and the results indicate that the proposed method performs well in detecting and identifying the various common image postprocessing operations. Furthermore, comparisons between the proposed approach and the existing methods show the superiority of the proposed approach.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Digital Media Forensic Detection · Image Processing Techniques and Applications · Cell Image Analysis Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Information Technology, Macau University of Science and Technology, Macau 853, China
Zhuhai MUST Science & Technology Research Institute, Zhuhai 519000, China
Funding
National Natural Science Foundation of China
References (30)
Show source-provided references
1. Identification of bitmap compression history: JPEG detection and quantizer estimation10.1109/TIP.2002.807361 ↗
2. Exposing digital forgeries from JPEG ghosts10.1109/TIFS.2008.2012215 ↗
3. JPEG Error Analysis and Its Applications to Digital Image Forensics10.1109/TIFS.2010.2051426 ↗
4. Detection of Nonaligned Double JPEG Compression Based on Integer Periodicity Maps10.1109/TIFS.2011.2170836 ↗
5. Contrast Enhancement-Based Forensics in Digital Images10.1109/TIFS.2014.2300937 ↗
6. Stamm, M., and Liu, K.J.R. (2008, January 12–15). Blind forensics of contrast enhancement in digital images. Proceedings of the 15th IEEE International Conference on Image Processing, San Diego, CA, USA.10.1109/ICIP.2008.4712454 ↗
7. Exposing digital forgeries by detecting traces of resampling10.1109/TSP.2004.839932 ↗
8. Blind Authentication Using Periodic Properties of Interpolation10.1109/TIFS.2004.924603 ↗
9. Li, L., Xue, J., Tian, Z., and Zheng, N. (, January October). Moment feature based forensic detection of resampled digital images. Proceedings of the 21st ACM International Conference on Multimedia, Barcelona, Spain.
10. Resampling detection aided steganalysis of heterogeneous bitmap images10.1117/1.JEI.22.1.013037 ↗
11. Blind Detection of Median Filtering in Digital Images: A Difference Domain Based Approach10.1109/TIP.2013.2277814 ↗
12. Kang, X., Stamm, M.C., Peng, A., and Liu, K.J.R. (2012, January 3–6). Robust median filtering forensics based on the autoregressive model of median filtered residual. Proceedings of the 2012 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, Hollywood, CA, USA.
13. Kirchner, M., and Fridrich, J. (2010). On detection of median filtering in digital images. Media Forensics and Security II, SPIE. 754110.10.1117/12.839100 ↗
14. Blind Forensics of Median Filtering in Digital Images10.1109/TIFS.2011.2161761 ↗
15. Steganalysis versus Splicing Detection10.1007/978-3-540-92238-4_13 ↗
16. Digital image splicing detection based on Markov features in DCT and DWT domain10.1016/j.patcog.2012.05.014 ↗
17. Passive Image-Splicing Detection by a 2-D Noncausal Markov Model10.1109/TCSVT.2014.2347513 ↗
18. Kao, H.-H., and Wen, C.-Y. (2020). An Offline Signature Verification and Forgery Detection Method Based on a Single Known Sample and an Explainable Deep Learning Approach. Appl. Sci., 10.10.3390/app10113716 ↗
19. Hsu, C.-C., Zhuang, Y.-X., and Lee, C.-Y. (2020). Deep Fake Image Detection Based on Pairwise Learning. Appl. Sci., 10.10.3390/app10010370 ↗
20. Rao, Y., and Ni, J. (2016, January 4–7). A deep learning approach to detection of splicing and copy-move forgeries in images. Proceedings of the 2016 IEEE International Workshop on Information Forensics and Security, Abu Dhabi, UAE.10.1109/WIFS.2016.7823911 ↗
21. Two-class 3D-CNN classifiers combination for video copy detection10.1007/s11042-018-6047-9 ↗
22. Identification of Various Image Operations Using Residual-based Features10.1109/TCSVT.2016.2599849 ↗
23. Rich Models for Steganalysis Digital Images10.1109/TIFS.2012.2190402 ↗
24. Ensemble Classifiers for Steganalysis of Digital Media10.1109/TIFS.2011.2175919 ↗
25. Huang, T., and Yuan, X. (2018, January 15–18). Detection and Classification of Various Image Operations Using Deep Learning Technology. Proceedings of the 2018 International Conference on Machine Learning and Cybernetics (ICMLC), Chengdu, China.10.1109/ICMLC.2018.8526999 ↗
26. Pattern classification using neural networks10.1109/35.41401 ↗
27. Gradient-based learning applied to document recognition10.1109/5.726791 ↗
28. ImageNet classification with deep convolutional neural networks
29. Filler, T., Pevný, T., Craver, S., and Ker, A. (2011). Break our steganographic system: The ins and outs of organizing BOSS. Information Hiding, Springer. IH 2011. Lecture Notes in Computer Science, Vol 6958.10.1007/978-3-642-24178-9 ↗
30. Steganalysis by Subtractive Pixel Adjacency Matrix10.1109/TIFS.2010.2045842 ↗