2025年 04期

摘要(Abstract)：

为了有效检测识别被篡改的古籍文字图像，提出一种可用于古籍文字图像篡改的检测识别模型MDAS-Net。首先在边缘监督分支中提出一种全新的特征融合方式即混合注意力块，以更好地提取图像中的多尺度目标信息；其次，针对边缘监督分支和噪声敏感分支的特征融合设计一种特征传递模块E-2-N/N-2-E Help Block,促进2个分支间的信息交流，以得到更高质量的融合特征。为了验证模型的有效性，创建古籍图像篡改数据集，并联合篡改图像文本数据集(TTI)进行对比实验和消融实验。结果表明，MDAS-Net模型在古籍文字图像篡改区域检测效果良好，受试者工作特性曲线下的面积(AUC)达到了0.852,F_1值达到了0.784,并证明了MDAS-Net在检测古籍文字图像篡改方面的实用性。

关键词(KeyWords)：图像处理;特征融合;图像篡改检测;古籍文字图像;深度学习

基金项目(Foundation):国家自然科学基金项目(62361053)

作者(Author): 李永博,钱永刚,刘青,马雨琪,伍胜,于显平,陈善雄

DOI:10.13349/j.cnki.jdxbn.20250509.001

参考文献(References)：

[1] RAO Y,NI J Q.A deep learning approach to detection of splicing and copy-move forgeries in images[C]//2016 IEEE International Workshop on Information Forensics and Security (WIFS),December 4-7,2016,Abu Dhabi,UAE.New York:IEEE,2016:1-6.

[2] ZHANG Y,GOH J,WIN L L,et al.Image region forgery detection:a deep learning approach[C]//MATHUR A,ROY-CHOUD-HURY A.Proceedings of the Singapore Cyber-Security Conference (SG-CRC) 2016.Amsterdam:IOS Press,2016:1-11.

[3] BAPPY J H,ROY-CHOWDHURY A K,BUNK J,et al.Exploiting spatial structure for localizing manipulated image regions[C]//2017 IEEE Iternational Conference on Computer Vision(ICCV),October 22-29,2017,Venice,Italy.New York:IEEE,2017:4980-4989.

[4] BUNK J,BAPPY J H,MOHAMMED T M,et al.Detection and localization of image using resampling features and deep learning[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPR),July 21-26,2017.Honolulu,HI,USA.New York:IEEE,2017:1881-1889.

[5] BONDI L,LAMERI S,GüERA D,et al.Tampering detection and localization through clustering of camera-based CNN features[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPR).July 21-26,2017.Honolulu,HI,USA.New York:IEEE,2017:1855-1864.

[6] LIU B,PUN C M.Deep fusion network for splicing forgery local-ization[C]//LEAL-TAIXé L,ROTH S.Computer Vision-ECCV 2018 Workshops.Cham:Springer Cham,2018:237-251.

[7] WU Y,ABD-ALMAGEED W,NATARAJAN P.Deep matching and validation network:an end-to-end solution to constrained image splicing localization and detection[C]//MM’17:Proceedings of the 25th ACM International Conference on Multimedia,October 23-27,2017,Mountain View,California,USA.New York:ACM,2017:1480-1502.

[8] CHEN C,McCLOSKEY S,YU J.Image splicing detection via camera response function analysis[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPR),July 21-26,2017.Honolulu,HI,USA.New York:IEEE,2017:1876-1885.

[9] BI X L,WEI Y,XIAO B,et al.RRU-Net:the ringed residual U-Net for image splicing forgery detection[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops,June 16-17,2019,Long Beach,CA,USA.New York:IEEE,2019:30-39.

[10] MA Y Q,CHEN S X,LI Y B,et al.STEF:a swin transformer-based enhanced feature pyramid fusion model for Dongba character detection[J].Heritage Science,2024,12:206.

[11] LI H D,HUANG J W.Localization of deep inpainting using high-pass fully convolutional network[C]//2019 IEEE/CVF International Conference on Computer Vision(ICCV),October 27-November 2,2019,Seoul,Republic of Korea.New York:IEEE,2019:8300-8309.

[12] YANG C,LI H Z,LIN F T,et al.Constrained R-CNN:a general image manipulation detection model[C]//2020 IEEE International Conference on Multimedia and Expo (ICME 2020 London),July 6-10,2020,London,UK.New York:IEEE,2020:1-6.

[13] HU X F,ZHANG Z H,JIANG Z Y,et al.SPAN:spatial pyramid attention network for image manipulation localization[C]//Computer Vision-ECCV 2020:16th European Conference,August 23-28,2020,Glasgow,UK.Cham:Springer,2020:312-328.

[14] WU Y,ABD-ALMAGEED W,NATARAJAN P.ManTra-Net:anipulation tracing network for detection and localization of image forgeries with anomalous features[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR),June 15-20,2019,Long Beach,CA,USA.New York:IEEE,2019:9535-9544.

[15] ZHOU P,HAN X T,MORARIU V I,et al.Learning rich features for image manipulation detection[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition,June 18-23,2018,Salt Lake City,UT,USA.New York:IEEE,2018:1053-1061.

[16] SALLOUM R,REN Y Z,KUO C C J.Image splicing localization using a multi-task fully convolutional network (MFCN)[J].Journal of Visual Communication and Image Representation,2018,51:201-209.

[17] ZHOU P,CHEN B C,HAN X T,et al.Generate,segment,and refine:towards generic manipulation segmentation[C]//Proceedings of the AAAI Conference on Artificial Intelligence:Vol.34,No.7:AAAI-20 Technical Tracks 7.Palo Alto:AAAI Press,2020:13058-13065.

[18] CHEN X R,DONG C B,JI J Q,et al.Image manipulation detection by multi-view multi-scale supervision[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision(ICCV),October 10-17,2021,Montreal,QC,Canada.New York:IEEE,2021:14165-14173.