[1]刘亚奇,蔡强,石磊,等.尺度可变有约束图像拼接检测与定位及其对抗优化[J].智能系统学报,2024,19(6):1479-1491.[doi:10.11992/tis.202307011]
LIU Yaqi,CAI Qiang,SHI Lei,et al.Scalable constrained image splicing detection and localization with adversarial optimizing[J].CAAI Transactions on Intelligent Systems,2024,19(6):1479-1491.[doi:10.11992/tis.202307011]
点击复制
LIU Yaqi,CAI Qiang,SHI Lei,et al.Scalable constrained image splicing detection and localization with adversarial optimizing[J].CAAI Transactions on Intelligent Systems,2024,19(6):1479-1491.[doi:10.11992/tis.202307011]
尺度可变有约束图像拼接检测与定位及其对抗优化
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
19
期数:
2024年第6期
页码:
1479-1491
栏目:
学术论文—智能系统
出版日期:
2024-12-05
- Title:
- Scalable constrained image splicing detection and localization with adversarial optimizing
- Keywords:
- constrained image splicing detection and localization; scalable; correlation computation; adversarial learning; image forensics ; atrous convolution; pyramid pooling; depthwise separable convolution
- 分类号:
- TP391.4
- 摘要:
- 针对有约束图像拼接检测与定位这一图像取证任务，提出一种尺度可变的检测与定位方法及其对抗优化架构。在所提有约束图像拼接检测与定位网络中，设计基于高效通道注意力增强的尺度可变关联性计算模型，采用高效通道注意力增强对通道特征进行校准，利用强关联因子截断操作实现处理任意尺度大小的图像；设计一种空间注意力增强的空洞空间金字塔池化对多尺度信息进行挖掘，以及基于深度可分离卷积和残差结构的定位结果重构网络。此外，提出一种块级对抗学习机制对预训练的尺度可变有约束图像拼接检测与定位网络进行优化。在公开数据集上的大量实验证明所提方法的有效性。
- Abstract:
- A scalable detection and localization method, along with its adversarial optimization architecture, is proposed for the image forensics task of constrained image splicing detection and localization (CISDL). In the CISDL network, a novel scalable correlation computation module is constructed using high-efficiency channel attention enhancement blocks. The channel features are then calibrated using high-efficiency channel attention enhancement. Images of arbitrary sizes are processed using truncation operations on closely correlated factors, and a mask reconstruction network is designed based on depthwise separable convolution and residual connections. Finally, a patch-level adversarial learning strategy is proposed to optimize the pretrained model. Extensive experiments on publicly available datasets demonstrate the effectiveness of the proposed method
- 参考文献/References:
-
[1] VERDOLIVA L. Media forensics and DeepFakes: an overview[J]. IEEE journal of selected topics in signal processing, 2020, 14(5): 910-932.
[2] COZZOLINO D, VERDOLIVA L. Noiseprint: a CNN-based camera model fingerprint[J]. IEEE transactions on information forensics and security, 2020, 15: 144-159.
[3] WANG Junke, WU Zuxuan, OUYANG Wenhao, et al. M2TR: multi-modal multi-scale transformers for deepfake detection[C]//Proceedings of the 2022 International Conference on Multimedia Retrieval. Newark: ACM, 2022: 615-623.
[4] LIU Yaqi, XIA Chao, ZHU Xiaobin, et al. Two-stage copy-move forgery detection with self deep matching and proposal SuperGlue[J]. IEEE transactions on image processing, 2022, 31: 541-555.
[5] ZHANG Yulan, ZHU Guopu, WU Ligang, et al. Multi-task SE-network for image splicing localization[J]. IEEE transactions on circuits and systems for video technology, 2022, 32(7): 4828-4840.
[6] BAMMEY Q, VON GIOI R G, MOREL J M. An adaptive neural network for unsupervised mosaic consistency analysis in image forensics[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 14182-14192.
[7] LIU Yaqi, GUAN Qingxiao, ZHAO Xianfeng, et al. Image Forgery Localization based on Multi-Scale Convolutional Neural Networks[C]//Proceedings of the 6th ACM Workshop on Information Hiding and Multimedia Security. Innsbruck: ACM, 2018: 85-90.
[8] PENG Bo, WANG Wei, DONG Jing, et al. Image forensics based on planar contact constraints of 3D objects[J]. IEEE transactions on information forensics and security, 2018, 13(2): 377-392.
[9] DAS S, ISLAM M S, AMIN M R. GCA-net: utilizing gated context attention for improving image forgery localization and detection[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. New Orleans: IEEE, 2022: 81-90.
[10] WANG Junke, WU Zuxuan, CHEN Jingjing, et al. ObjectFormer for image manipulation detection and localization[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022: 2354-2363.
[11] LIU Yaqi, LYU Binbin, JIN Xin, et al. TBFormer: two-branch transformer for image forgery localization[J]. IEEE signal processing letters, 2023, 30: 623-627.
[12] WU Yue, ABD-ALMAGEED W, NATARAJAN P. Deep matching and validation network: an end-to-end solution to constrained image splicing localization and detection[C]//Proceedings of the 25th ACM international conference on Multimedia. Mountain View: ACM, 2017: 1480-1502.
[13] LIU Yaqi, ZHU Xiaobin, ZHAO Xianfeng, et al. Adversarial learning for constrained image splicing detection and localization based on atrous convolution[J]. IEEE transactions on information forensics and security, 2019, 14(10): 2551-2566.
[14] LIU Yaqi, ZHAO Xianfeng. Constrained image splicing detection and localization with attention-aware encoder-decoder and atrous convolution[J]. IEEE access, 2020, 8: 6729-6741.
[15] MOREIRA D, BHARATI A, BROGAN J, et al. Image provenance analysis at scale[J]. IEEE transactions on image processing, 2018, 27(12): 6109-6123.
[16] YE Kui, DONG Jing, WANG Wei, et al. Feature pyramid deep matching and localization network for image forensics[C]//2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference. Honolulu: IEEE, 2018: 1796-1802.
[17] WAN Ji, WANG Dayong, HOI S C H, et al. Deep learning for content-based image retrieval: a comprehensive study[C]//Proceedings of the 22nd ACM international conference on Multimedia. Orlando: ACM, 2014: 157-166.
[18] PINTO A, MOREIRA D, BHARATI A, et al. Provenance filtering for multimedia phylogeny[C]//2017 IEEE International Conference on Image Processing. Beijing: IEEE, 2017: 1502-1506.
[19] LI Yuanman, ZHOU Jiantao. Fast and effective image copy-move forgery detection via hierarchical feature point matching[J]. IEEE transactions on information forensics and security, 2019, 14(5): 1307-1322.
[20] 王凯诚, 鲁华祥, 龚国良, 等. 基于注意力机制的显著性目标检测方法[J]. 智能系统学报, 2020, 15(5): 956-963.
WANG Kaicheng, LU Huaxiang, GONG Guoliang, et al. Salient object detection method based on the attention mechanism[J]. CAAI transactions on intelligent systems, 2020, 15(5): 956-963.
[21] 李涛, 高志刚, 管晟媛, 等. 结合全局注意力机制的实时语义分割网络[J]. 智能系统学报, 2023, 18(2): 282-292.
LI Tao, GAO Zhigang, GUAN Shengyuan, et al. Global attention mechanism with real-time semantic segmentation network[J]. CAAI transactions on intelligent systems, 2023, 18(2): 282-292.
[22] CHOLLET F. Xception: deep learning with depthwise separable convolutions[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 1800-1807.
[23] WANG Qilong, WU Banggu, ZHU Pengfei, et al. ECA-net: efficient channel attention for deep convolutional neural networks[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 11531-11539.
[24] CHRISTLEIN V, RIESS C, JORDAN J, et al. An evaluation of popular copy-move forgery detection approaches[J]. IEEE transactions on information forensics and security, 2012, 7(6): 1841-1854.
[25] LUO Weiqi, HUANG Jiwu, QIU Guoping. Robust detection of region-duplication forgery in digital image[C]//18th International Conference on Pattern Recognition. Hong Kong: IEEE, 2006: 746-749.
[26] RYU S J, LEE M J, LEE H K. Detection of copy-rotate-move forgery using zernike moments[M]//Lecture Notes in Computer Science. Berlin: Springer Berlin Heidelberg, 2010: 51-65.
[27] COZZOLINO D, POGGI G, VERDOLIVA L. Efficient dense-field copy-move forgery detection[J]. IEEE transactions on information forensics and security, 2015, 10(11): 2284-2297.
备注/Memo
收稿日期:2023-7-12。
基金项目:中央高校基本科研业务费资金项目（3282023016）；国家自然科学基金项目（62102010, 62002003）；北京工商大学食品安全大数据技术北京市重点实验室开放课题（BTBD-2022KF02）.
作者简介:刘亚奇，助理研究员，博士，主要研究领域为多媒体安全、图像取证、人工智能和模式识别。E-mail：liuyaqi@besti.edu.cn;蔡强，教授，博士，主要研究方向为计算机图形学、计算几何、科学可视化、智能信息处理。发表学术论文90余篇。E-mail：caiq@btbu.edu.cn;石磊，副研究员，博士，中国人工智能学会智能服务专委会委员，主要研究方向为智能信息处理、大数据分析与挖掘、社交网络搜索及人工智能。E-mail：leiky_shi@cuc.edu.cn。
通讯作者:蔡强. E-mail：caiq@btbu.edu.cn
更新日期/Last Update:
2024-11-05