Abstract
Although most of the current image manipulation detection algorithms gain great breakthrough, it still generally has problems in detecting multiple types of tampering techniques, and in receiving the classification, detection and segmentation results simultaneously. We propose a two streams network driven by segmentation mask, called T-SAMnet, where RGB images and noise images provide semantic features and noise inconsistency features for the network respectively. RGB stream generates tampered region detection bounding box and segmentation mask, and then is fused with the noise stream to generate classification results. The segmentation mask, on the one hand, supervises the characteristics of the network learning tampered region, feeds back as segmentation attention mechanism to constraint detection branch. The experimental results demonstrates that our method achieves state-of-the-art performance on the three standard image manipulation detection datasets.
This work was supported in part by the National Natural Science Foundation of China under Grants 61571382, 81671766, 61571005, 81671674, 61671309, 61971369 and U1605252, in part by the Fundamental Research Funds for the Central Universities under Grants 20720160075 and 20720180059, in part by the CCF-Tencent open fund, and the Natural Science Foundation of Fujian Province of China (No. 2017J01126).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Farid, H.: Creating and detecting doctored and virtual images: implications to the child pornography prevention act. Department of Computer Science, Dartmouth College, TR2004-518, 13:970 (2004)
Wu, Q., Li, G., Tu, D., Sun, S.: A survey of blind digital image forensics technology for authenticity detection. Acta Autom. Sinica 34(12), 1458–1466 (2008)
Zhou, P., Han, X., Morariu, V.I., Davis, L.S.: Learning rich features for image manipulation detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1053–1061 (2018)
Ng, T.T., Chang, S.F.: A model for image splicing. In: 2004 IEEE International Conference on Image Processing, vol. 2, pp. 1169–1172 (2004)
Zhou, Z., Hu, C., Huang, H.: Image blur forgery detection based on color consistency. Comput. Eng. 42(1), 237–242 (2016)
Fridrich, J., Kodovsky, J.: Rich models for steganalysis of digital images. IEEE Trans. Inf. Forensics Secur. 7(3), 868–882 (2012)
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, pp. 1–6 (2016)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Gao, Y., Beijbom, O., Zhang, N.: Compact bilinear pooling. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 317–326 (2016)
Fu J., Zheng, H., Mei, T.: Look closer to see better: recurrent attention convolutional neural network for finegrained image recognition. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (2017)
Nist nimble 2016 datasets. https://www.nist.gov/itl/iad/mig/nimble-challenge-2017-evaluation/
Dong, J., Wang W., Tan, T.: Casia image tampering detection evaluation database (2010). http://forensics.idealtest.org
Dong, J., Wang, W., Tan, T.: Casia image tampering detection evaluation database. In: 2013 IEEE China Summit and International Conference on Signal and Information Processing, pp. 422–426 (2013)
Wen, B., Zhu, Y., Subramanian, R., Ng, T.-T., Shen, X., Winkler, S.: COVERAGEA novel database for copy-move forgery detection. In: 2016 IEEE International Conference on Image Processing, pp. 161–165 (2016)
Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48
Krawetz, N.: A picture’s worth.... Hacker Factor Solutions 6, 2 (2007)
Mahdian, B., Saic, S.: Using noise inconsistencies for blind image forensics. Image Vis. Comput. 27(10), 1497–1503 (2009)
Ferrara, P., Bianchi, T., De Rosa, A.: Image forgery localization via finegrained analysis of CFA artifacts. IEEE Trans. Inf. Forensics Secur. 7(5), 1566–1577 (2012)
Dirik, A.E., Memon, N.: Image tamper detection based on demosaicing artifacts. In: 2009 IEEE International Conference on Image Processing, pp. 1497–1500 (2009)
Salloum, R., Ren, Y., Kuo, C.C.J.: Image splicing localization using a multi-task fully convo-lutional network (MFCN). J. Vis. Commun. Image Represent. 51, 201–209 (2018)
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
Pan, J., Chen, Y., Huang, Y., Ding, X., Cheng, E. (2019). T-SAMnet: A Segmentation Driven Network for Image Manipulation Detection. In: Gedeon, T., Wong, K., Lee, M. (eds) Neural Information Processing. ICONIP 2019. Communications in Computer and Information Science, vol 1143. Springer, Cham. https://doi.org/10.1007/978-3-030-36802-9_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-36802-9_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-36801-2
Online ISBN: 978-3-030-36802-9
eBook Packages: Computer ScienceComputer Science (R0)