Abstract
With the introduction of AI technology in the field of image inpainting, it makes up for the shortcomings of traditional inpainting methods. Since this technology can achieve object removal without obvious traces by learning visual semantics informations and performs better in complex environment, it brings great challenges to the existing image forensics work. So far, there are few detection methods for AI image inpainting forgery. In order to fill the gap in this field, this paper proposes a deep learning-based detection method. Considering Faster R-CNN model has demonstrated good performance on detecting semantic objects over a range of scales, we migrate it to the forensic field for image inpainting forgery. It turns out that Faster R-CNN model can capture inconsistencies features between the inpainted region and the authentic region. Therefore, this can further enrich the application range of digital image forensics algorithms. We construct a large-scale AI image inpainting dataset based on ImageNet dataset. The experimental results on this dataset demonstrate that our proposed approach achieves good performance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Taimori, A., Razzazi, F., Behrad, A., Ahmadi, A., Babaie-Zadeh, M.: A novel forensic image analysis tool for discovering double JPEG compression clues. Multimed. Tools Appl. 76(6), 1–35 (2017)
Kang, H.R.: Median filtering detection using variation of neighboring line pairs for image forensic. In: IEEE International Conference on Consumer Electronics, Berlin, vol. 25, pp. 103–107 (2016)
Li, J., Yang, F., Lu, W., Sun, W.: Keypoint-based copy-move detection scheme by adopting MSCRs and improved feature matching. Multimed. Tools Appl. 76, 20483–20497 (2016)
Criminisi, A., Perez, P., Toyama, K.: Region filling and object removal by exemplar-based image inpainting. IEEE Trans. Image Process. 13(9), 1200–1212 (2004)
Zhou, C., Wang, Z., Liu, S., Astronautics, S.O.: Method of image restoration directly based on spatial varied point spread function. Acta Opt. Sin. 37(1), 110–121 (2017)
Pathak, D., Krahenbuhl, P, Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: Computer Vision and Pattern Recognition, CVPR, pp. 2536–2544 (2016)
Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., Huang, T.S.: Generative image inpainting with contextual attention. arXiv:1801.07892 (2018)
Wu, Q., Sun, S.J., Zhu, W., Li, G.H., Tu, D.: Detection of digital doctoring in exemplar-based inpainted images. In: Proceedings of IEEE International Conference on Machine Learning and Cybernetics, vol. 3, pp. 1222–1226 (2008)
Liang, Z., Yang, G., Ding, X., Li, L.: An efficient forgery detection algorithm for object removal by exemplar-based image inpainting. J. Vis. Commun. Image Represent. 30(C), 75–85 (2015)
Meng, R., Rice, S.G., Wang, J., Sun, X.: A fusion steganographic algorithm based on faster R-CNN. CMC: Comput. Mater. Contin. 55(1), 001–016 (2018)
Li, C., Jiang, Y., Cheslyar, M.: Embedding image through generated intermediate medium using deep convolutional generative adversarial network. CMC: Comput. Mater. Contin. 56(2), 313–324 (2018)
Badrinarayanan, V., Kendall, A., Cipolla, R.: SegNet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2481–2495 (2017)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137–1149 (2017)
Bayar, B., Stamm, M.C.: A deep learning approach to universal image manipulation detection using a new convolutional layer. In: Proceedings of the 4th ACM Workshop on Information Hiding and Multimedia Security, pp. 5–10 (2016)
Bayar, B., Stamm, M.C.: Design principles of convolutional neural networks for multimedia forensics. Electron. Imaging 2017(7), 77–86 (2017)
Rao, Y., Ni, J.: A deep learning approach to detection of splicing and copy-move forgeries in images. In: 2016 IEEE International Workshop on Information Forensics and Security (WIFS), pp. 1–6. IEEE (2016)
Bayar, B., Stamm, M.C.: On the robustness of constrained convolutional neural networks to JPEG post-compression for image resampling detection. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 2152–2156 (2017)
Gao, R., Grauman, K.: On-demand learning for deep image restoration. In: IEEE International Conference on Computer Vision, pp. 1095–1104 (2017)
Yang, C., et al.: High-resolution image inpainting using multi-scale neural patch synthesis. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, pp. 4076–4084 (2017)
Girshick, R.: Fast R-CNN. In: IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)
Acknowledgements
This work was supported by National Natural Science Foundation of China (No. 61370195, U1536121).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, X., Wang, H., Niu, S. (2019). An Image Forensic Method for AI Inpainting Using Faster R-CNN. In: Sun, X., Pan, Z., Bertino, E. (eds) Artificial Intelligence and Security. ICAIS 2019. Lecture Notes in Computer Science(), vol 11634. Springer, Cham. https://doi.org/10.1007/978-3-030-24271-8_43
Download citation
DOI: https://doi.org/10.1007/978-3-030-24271-8_43
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-24270-1
Online ISBN: 978-3-030-24271-8
eBook Packages: Computer ScienceComputer Science (R0)