基于注意力机制的图像篡改检测
Image Tampering Detection Based on Attention Mechanism
DOI: 10.12677/CSA.2022.123074, PDF,    科研立项经费支持
作者: 余 晨, 朱 烨：成都信息工程大学计算机学院，四川 成都；符 颖：成都信息工程大学计算机学院，四川 成都;四川省图形图像与空间信息2011协同创新中心，四川 成都
关键词: 图像篡改；分割；注意力机制；Image Tampering； Segmentation； Attention Mechanism
摘要: 目前已有的基于分割的图像篡改检测方法由于标注困难，可用的篡改数据集较少，造成训练数据的缺乏，同时篡改图像经过处理后边界难以识别，导致分割精度低。针对上述问题提出了基于注意力机制的图像篡改检测网络，该网络实现了篡改图像的生成，篡改区域的分割和优化。其中，生成器创建篡改图像用于扩充训练数据，基于注意力机制的分割优化模块用于增强篡改区域边界的特征提取能力，最后以实验结果证明了此方法的准确性和有效性。
Abstract: At present, the existing image tamper detection methods based on segmentation are difficult to label and have few available tamper data sets, resulting in the lack of training data. At the same time, the boundary of the tampered image is difficult to identify after processing, resulting in low segmentation accuracy. To solve the above problems, an image tamper detection network based on attention mechanism is proposed. The network realizes the generation of tampered images, the segmentation and optimization of tampered regions. The generator creates the tampered image to expand the training data, and the segmentation optimization module based on attention mechanism is used to enhance the feature extraction ability of the tampered region boundary. Finally, the experimental results show the accuracy and effectiveness of this method.
文章引用：余晨, 符颖, 朱烨. 基于注意力机制的图像篡改检测[J]. 计算机科学与应用, 2022, 12(3): 729-738. https://doi.org/10.12677/CSA.2022.123074

参考文献

[1] Lu, C.S., et al. (2003) Structural Digital Signature for Image Authentication: An Incidental Distortion Resistant Scheme. IEEE Transactions on Multimedia, 5, 161-173. [Google Scholar] [CrossRef] 
[2] Weng, S., Yao, Z., Pan, J.S., et al. (2008) Reversible Watermarking Based on Invariability and Adjustment on Pixel Pairs. IEEE Signal Processing Letters, 15, 721-724. [Google Scholar] [CrossRef] 
[3] Fridrich, A.J., Soukal, B.D. and Luk, S.A.J. (2003) Detection of Copy-Move Forgery in Digital Images. Proceedings of Digital Forensic Research Workshop, Cleveland, 6-8 August 2003, 55-61.
[4] Popescu, A.C. and Farid, H. (2004) Exposing Digital Forgeries by Detecting Duplicated Image Regions. Department of Computer Science, Dartmouth College, Hanover, Tech. Rep. TR2004-515, 1-11.
[5] Liu, Y., Guan, Q., Zhao, X., et al. (2018) Image Forgery Localization Based on Multi-Scale Convolutional Neural Networks. Proceedings of the 6th ACM Workshop on Information Hiding and Multimedia Security, Innsbruck, 20-22 June 2018, 85-90. [Google Scholar] [CrossRef] 
[6] Liu, B. and Pun, C.-M. (2018) Deep Fusion Network for Splicing Forgery Localization. Proceedings of the European Conference on Computer Vision (ECCV), Munich, 8-14 September 2018, 237-251. [Google Scholar] [CrossRef] 
[7] Huh, M., Liu, A., Owens, A., et al. (2018) Fighting Fake News: Image Splice Detection via Learned Self-Consistency. Proceedings of the European Conference on Computer Vi-sion (ECCV), Munich, 8-14 September 2018, 106-124. [Google Scholar] [CrossRef] 
[8] Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A. and Bengio, Y. (2014) Generative Adversarial Nets. Advances in Neural In-formation Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, Montreal, 8-13 December 2014, 2672-2680.
[9] Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K. and Yuille, A.L. (2018) DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40, 834-848. [Google Scholar] [CrossRef] 
[10] Woo, S., Park, J., Lee, J.Y., et al. (2018) Cbam: Convolutiona Block Attention Module. Proceedings of the European Conference on Computer Vision (ECCV), Munich, 8-14 Septem-ber 2018, 3-19. [Google Scholar] [CrossRef] 
[11] Ronneberger, O., Fischer, P. and Brox, T. (2015) U-net: Con-volutional Networks for Biomedical Image Segmentation. 18th International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, 5-9 October 2015, 234-241. [Google Scholar] [CrossRef] 
[12] Isola, P., Zhu, J.-Y., Zhou, T. and Efros, A.A. (2017) Im-age-to-Image Translation with Conditional Adversarial Networks. 2017 IEEE Conference on Computer Vision and Pat-tern Recognition (CVPR), Honolulu, 21-26 July 2017, 5967-5976. [Google Scholar] [CrossRef] 
[13] Dong, J., Wang, W. and Tan, T. (2013) Casia Image Tampering De-tection Evaluation Database. 2013 IEEE China Summit and International Conference on Signal and Information Pro-cessing, ChinaSIP 2013, Beijing, 6-10 July 2013, 422-426. [Google Scholar] [CrossRef] 
[14] Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollar, P. and Zitnick, C.L. (2014) Microsoft Coco: Common Objects in Context. Computer Vi-sion—ECCV 2014: 13th European Conference, Zurich, 6-12 September 2014, 740-755. [Google Scholar] [CrossRef] 
[15] Perez, P., Gangnet, M. and Blake, A. (2003) Poisson Image Editing. ACM Transactions on Graphics, 22, 313-318. [Google Scholar] [CrossRef] 
[16] Mahdian, B. and Saic, S. (2009) Using Noise Inconsistencies for Blind Image Forensics. Image and Vision Computing, 27, 1497-1503. [Google Scholar] [CrossRef] 
[17] Ferrara, P., Bianchi, T., De Rosa, A. and Piva, A. (2012) Image Forgery Localization via Fine-Grained Analysis of CFA Artifacts. IEEE Transactions on Information Forensics and Security, 7, 1604-1613. [Google Scholar] [CrossRef] 
[18] Salloum, R., Ren, Y. and Kuo, C. (2017) Image Splicing Locali-zation Using a Multi-Task Fully Convolutional Network (MFCN). Journal of Visual Communication & Image Repre-sentation, 51, 201-209. [Google Scholar] [CrossRef] 
[19] Zhou, P., Chen, B.-C., Han, X., Najibi, M., Shrivastava, A., Lim, S.-N. and Davis, L. (2020) Generate, Segment, and Refine: Towards Generic Manipulation Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 34, 13058-13065. [Google Scholar] [CrossRef]