ABSTRACT
Imaging device recognition is an important research hotspot in image tampering analysis. In recent years, it has received extensive research and rapid development. Image tampering analysis based on imaging devices is an important field in image tampering, and the recognition of imaging devices has also become important. In order to promote the recognition research based on imaging equipment, this paper summarizes and discusses the current main methods and representative work of imaging equipment identification. This article compares the similarities and differences of traditional methods and related deep learning methods, respectively, and details the current The main principles and methods of imaging device recognition based on deep learning are discussed. Finally, the problems that need to be solved for imaging device recognition based on deep learning and the future research trends are discussed.
- A. Rocha, W. Scheirer, T. Boult, and S. Goldenstein, "Vision of the unseen: Current trends and challenges in digital image and video forensics," ACM Computing Surveys (CSUR), vol.43, pp. 26:1--26:42, 2011.Google ScholarDigital Library
- S. Bayram, H. Sencar, N. Memon, and I. Avcibas, "Source camera identification based on CFA interpolation," in IEEE International Conference on Image Processing (ICIP), 2005.Google Scholar
- S. Milani, P. Bestagini, M. Tagliasacchi, and S. Tubaro, "Demosaicing strategy identification via eigenalgorithms," in IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP), 2014.Google Scholar
- Geradts Z, Bijhold J, Kieft M, Kurosawa K, Kuroki K, Saitoh, N. Methods foridentification of images aequired with digital cameras[A]. Proc of SPIE, Enabling Tehnologies for Law Enfor cement and Security[C]. Stockholm, Sweden: Springer-Verlag, 2001: 505--512.Google ScholarCross Ref
- Hany Farid. Blind Inverse Gamma Correction[J]. IEEE Transactions on Image Proeessing, 2001, 10: 1428--1433.Google ScholarDigital Library
- Ng T T, Chang S F, Tsui M P. Camera response function estimation from a single-channel image using differential invariants[J]. 2006.Google Scholar
- Kharrazi M, Sencar H T, Memon N. Blind source camera identification[C]. International Conference on Image Processing. IEEE, 2004.Google ScholarCross Ref
- Min-Jen, Guan-Hui Wu. Using image features to identify camera sources[A]. Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference[C]. Toulouse, France: IEEE, 2006, 2: 297--300.Google Scholar
- Sevinc Bayram, Husrev T Senear, Nasir Memon. Source camera identification based on CFA interpolation[C]. IEEE Intemational Conference on Image Processing. Genoa, Italy:IEEE, 2005: 69--72.Google Scholar
- S. Bayram, H. T. Sencar, and N. Memon, "Improvements on source camera-model identification based on CFA interpolation," presented at the Working Group 11.9 Int. Conf. Digital Forensics, Orlando, FL, Jan. 2006.Google Scholar
- Long Y, Huang Y. Image based source camera identification using demosaicking. Proceedings of the 8th Workshop on Multimedia Signal Processing. Washington, DC:IEEE Computer Society, 2006, 419--424.Google Scholar
- Swaminathan A, Wu M, Liu K J R. Nonintrusive component forensics of visual sensors output images[J]. IEEE Trans. on Information Forensics and Security, 2007, 2(1):91--106.Google ScholarDigital Library
- Wang Bo, Kong XW, HX Fu. Image source forensics based on OC-SVM and MC-SVM [J]. Computer research and development, 2009, 46(9): 1456--1461.Google Scholar
- X.G. Kang, Y. Li, Z. Qu, and J.W. Huang. Enhancing source camera identification performance with a camera reference phase sensor pattern noise. IEEE Trans. On Information Forensics and Security, 2012.Google ScholarDigital Library
- Goljan M, Fridrich J, Lukas J. Camera identification from printed images. Proceedings ofSPIE, Electronic Imaging Forensics, Security, Steganography, and Watermarking ofMultimedia Contents X. San Jose, CA:SPIE, 2008:68190I.1 -- 68190I.12.Google Scholar
- C.-T. Li. Source camera identification using enhanced sensor pattern noise. IEEE Trans. on Information Forensics and Security, 2010.Google Scholar
- Camera model identification based on the characteristic of CFA and interpolation. In: IWDW'11 Proceedings of the 10th International Conference on Digital-Forensics and Watermarking; 2011 Oct 23--26; Atlantic City, NJ, USA. Berlin: Springer-Verlag;Google Scholar
- Bloy G J. Blind camera fingerprinting and image clustering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 30(3): 532--534.Google ScholarDigital Library
- Caldelli R, Amerini I, Picchioni F, et al. Fast image clustering of unknown source images[C]. In: Proceedings of IEEE International Workshop on Information Forensics and Security. Piscataway, NJ, USA: IEEE Press, 2010: 371--375.Google ScholarCross Ref
- Li C T. Unsupervised classification of digital images using enhanced sensor pattern noise[C]. In: Proceedings of IEEE International Symposium on Circuits and Systems. Piscataway, NJ, USA: IEEE Press, 2010: 3429--3432.Google ScholarCross Ref
- García Villalba L J, Sandoval Orozco A L, Corripio J R. Smartphone image clustering[J]. Expert Systems with Applications, 2015, 42(4): 1927--1940.Google ScholarDigital Library
- Caldelli R, Amerini I, Picchioni F, et al. Fast image clustering of unknown source images[C]. In: Proceedings of IEEE International Workshop on Information Forensics and Security. Piscataway, NJ, USA: IEEE Press, 2010: 371--375.Google ScholarCross Ref
- Fahmy O. An efficient clustering technique for cameras identification using sensor pattern noise[C]. In: Proceedings of International Conference on Systems, Signals and Image Processing. Piscataway, NJ, USA: IEEE Press, 2015: 249--252.Google ScholarCross Ref
- Yann LeCun, Leon Bottou, Yoshua Bengio, et al. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 1998, 86(11):2278--2324Google ScholarCross Ref
- Xuefeng Jiang, Yikun Wang, Wenbo Liu, et al. CapsNet, CNN, FCN: Comparative Performance Evaluation for Image Classification. International Journal of Machine Learning and Computing, 2019, 9(6):840--848.Google Scholar
- Bondi L, Baroffio L, Güera, David, et al. First Steps Toward Camera Model Identification with Convolutional Neural Networks[J]. IEEE Signal Processing Letters, 2016, 24(3):259--263.Google ScholarCross Ref
- Tuama A, Frédéric Comby, Chaumont M. Camera Model Identification With The Use of Deep Convolutional Neural Networks[C]. WIFS'2016, IEEE International Workshop on Information Forensics and Security. IEEE, 2016.Google ScholarCross Ref
- Baroffio, Luca & Bondi, Luca & Bestagini, Paolo & Tubaro, Stefano. (2016). Camera identification with deep convolutional networks.Google Scholar
- Bayar, Belhassen & Stamm, Matthew. Augmented convolutional feature maps for robust CNN-based camera model identification. 4098--4102. 10.1109/ICIP.2017.8297053.Google Scholar
- X. Kang, M. C. Stamm, A. Peng, and K. R. Liu, "Robust median filtering forensics using an autoregressive model," IEEE Transactions on Information Forensics and Security, vol. 8, no. 9, pp. 1456--1468, 2013Google ScholarDigital Library
- B. Bayar and M. C. Stamm, "A deep learning approach to universalimage manipulation detection using a new convolutionallayer," in Proceedings of the 4th ACM Workshop on Information Hiding and Multimedia Security. ACM, 2016, pp. 5--10.Google Scholar
- Yang P, Zhao W, Ni R, et al. Source Camera Identification Based On Content-Adaptive Fusion Network[J]. Pattern Recognition Letters, 2017.Google Scholar
- Freire-Obregon, D., narducci, F., Barra, S., & Castrillon-Santana, M.(2017). Deep learning for source camera identification on mobile devices. Eprint arXiv:1710.01257.Google Scholar
- Sameer V U, Naskar R, Musthyala N, et al. Deep Learning Based Counter--Forensic Image Classification for Camera Model Identification[C]. International Workshop on Digital Watermarking. 2017.Google ScholarCross Ref
- Bondi L, Lameri S, David Güera, et al. Tampering Detection and Localization Through Clustering of Camera-Based CNN Features[C]. Computer Vision & Pattern Recognition Workshops. IEEE, 2017.Google ScholarCross Ref
- Luca B, Güera David, Luca B, et al. A Preliminary Study on Convolutional Neural Networks for Camera Model Identification[C]. 2017:67--76.Google Scholar
- B. Bayar and M. C. Stamm. Towards open set camera model identification using a deep learning framework. In The 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2018.Google ScholarDigital Library
- Ding X, Chen Y, Tang Z, et al. Camera Identification Based on Domain Knowledge-Driven Deep Multi-Task Learning[J]. IEEE Access, 2019, 7:25878--25890Google ScholarCross Ref
Index Terms
- Review of Imaging Device Identification Based on Machine Learning
Recommendations
Review on deep learning fetal brain segmentation from Magnetic Resonance images
AbstractBrain segmentation is often the first and most critical step in quantitative analysis of the brain for many clinical applications, including fetal imaging. Different aspects challenge the segmentation of the fetal brain in magnetic resonance ...
Highlights- We reviewed 39 DL studies for fetal brain segmentation from MR images
- U-Net backbone is the dominant method for automatic fetal brain segmentation
- There is a segmentation performances convergence for the currently available ...
Radiological images and machine learning: Trends, perspectives, and prospects
AbstractThe application of machine learning to radiological images is an increasingly active research area that is expected to grow in the next five to ten years. Recent advances in machine learning have the potential to recognize and classify complex ...
Brain Tumor Classification using Machine Learning and Deep Learning Algorithms: A Comparison: Classifying brain MRI images on thebasis of location of tumor and comparingthe various Machine Learning and Deep LEARNING models used to predict best performance.
IC3-2022: Proceedings of the 2022 Fourteenth International Conference on Contemporary ComputingIn both children and middle aged adults, brain tumors are considered as one of the most dangerous diseases. Brain Tumors are classified as: Malignant Tumor, Benign Tumor, Pituitary Tumor, etc. During the MRI scans, massive volumes of data pictures are ...
Comments