基于双树复数小波四元数卷积网络的Copy-move盲取证算法

兰州理工大学学报 ›› 2021, Vol. 47 ›› Issue (2): 87-96.

• 自动化技术与计算机技术 • 上一篇下一篇

基于双树复数小波四元数卷积网络的Copy-move盲取证算法

李策^*, 李兰, 靳山岗, 高伟哲, 许大有

兰州理工大学电气工程与信息工程学院, 甘肃兰州 730050

收稿日期:2020-01-09 出版日期:2021-04-28 发布日期:2021-05-11
通讯作者: 李策(1974-),男,辽宁营口人,博士,教授,博导.Email:christ.cli@foxmail.com
基金资助:
国家自然科学基金(61866022),甘肃省基础研究创新群体项目(1506RJIA031)

Copy-move image blind forgery algorithm based on quaternion convolutional neural networks with dual-tree complex wavelet

LI Ce, LI Lan, JIN Shan-gang, GAO Wei-zhe, XU Da-you

College of Electrical and Information Engineering, Lanzhou Univ. of Tech., Lanzhou 730050, China

Received:2020-01-09 Online:2021-04-28 Published:2021-05-11

摘要/Abstract

摘要： 随着图像编辑软件的普及与完善,使得人们通过Copy-move操作便可伪造图像,而现有的Copy-move盲取证算法很难提取到彩色图像的一致性特征,且结果依赖于手动调节参数,难以定位到准确的篡改区域.为此,利用四元数卷积网络提取彩色图像空间一致性信息和双树复数小波提取图像局部信息的优势,提出了一种基于双树复数小波四元数卷积网络的Copy-move盲取证算法.首先,将图像表示为四元数并输入到四元数卷积网络中,提取彩色图像的颜色一致性特征,并将双树复数小波变换的高频子带与卷积网络的特征图联合学习图像的局部特征.其次,计算特征向量之间的相似性分数.然后,利用卷积网络提取较高分数的特征,定位相似区域,在一定程度上解决了匹配时手动调节参数的问题;并构建了一个仅定位粘贴区域的辅助分支来区分相似区域.最后,融合了相似和粘贴区域得到能够区分复制和粘贴位置的结果.在CoMoFoD和CASIA CMFD数据集上的主客观实验表明,该算法提升了Copy-move盲取证的定位性能.

关键词: Copy-move盲取证, 四元数卷积, 双树复数小波

Abstract: With the popularity of image editing software, people can forge images by Copy-move. However, existing Copy-move blind forensics algorithms are difficult to extract consistency features of color images with results depending on manually adjusting parameters, which leads to low locate accurate. Therefore, using the advantage of quaternion convolutional network on extracting spatial consistency of color images and double-tree complex wavelet on extracting image local features, Copy-move blind forensics algorithm based on quaternion convolutional network with double-tree complex wavelet is proposed. Firstly, images represented as quaternions were input to quaternion convolutional network to extract consistency features of color images, and the high-frequency subbands of double-tree complex wavelet transform were connected with feature maps of the convolutional network to learn local features. Next, similarity scores in feature vectors are calculated. Then, convolutional network is extracted features with higher scores to locate similar areas, which solves the problem of adjusting parameters during matching. Besides, an auxiliary branch is constructed to locate the tampered areas. Finally, similar and tampered areas are fused to distinguish copy and paste. The subjective and objective experiments on CoMoFoD and CASIA CMFD datasets show that the proposed algorithm improves the performance of Copy-move blind forgery.

Key words: Copy-move blind forgery, quaternion convolutional neural networks, the dual-tree complex wavelet

中图分类号:

TP393

李策, 李兰, 靳山岗, 高伟哲, 许大有. 基于双树复数小波四元数卷积网络的Copy-move盲取证算法[J]. 兰州理工大学学报, 2021, 47(2): 87-96.

LI Ce, LI Lan, JIN Shan-gang, GAO Wei-zhe, XU Da-you. Copy-move image blind forgery algorithm based on quaternion convolutional neural networks with dual-tree complex wavelet[J]. Journal of Lanzhou University of Technology, 2021, 47(2): 87-96.

参考文献

[1] 姚晔,胡伟通,任一支,等.数字视频区域篡改的检测与定位[J].中国图像图形学报,2018,23(6):779-791.
[2] 钱建波.基于多特征融合及能量分布的图像篡改检测方法[J].兰州理工大学学报,2018,44(4):97-102.
[3] RYU S J,LEE M J,KIRCHNER M,et al.Rotation invariant localization of duplicated image regions based on zernike moments[J].IEEE Transactions on Information Forensics and Security,2013,8(8):1355-1370.
[4] 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.
[5] 朱叶,申铉京,陈海鹏.基于彩色LBP 的隐蔽性复制-粘贴篡改盲鉴别算法[J].自动化学报,2017,43(3):391-397.
[6] 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.
[7] PUN C M,YUAN X C,BI X L.Image forgery detection using adaptive oversegmentation and feature point matching[J].IEEE Transactions on Information Forensics and Security,2015,10(8):1705-1716.
[8] BAPPY J H,ROY-CHOWDURY A,BUNK J,et al.Exploiting spatial structure for localizing manipulated image regions[C]//IEEE International Conference on Computer Vision.Venice,Italy:IEEE,2017:4970-4979.
[9] ZHOU P,HAN X,MORARIU V I,et al.Learning rich features for image manipulation detection[C]//IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake City:IEEE,2018:1053-1061.
[10] WU Y,ABD-ALMAGEED W,NATARAJAN P.BusterNet:Detecting copy-move image forgery with source/target localization[C]//European Conference on Computer Vision.[S.l.]:Springer,2018:168-184.
[11] ZHU X Y,XU Y,XU H T,et al.Quaternion convolutional neural networks[C]//European Conference on Computer Vision.[S.l.]:Springer,2018:631-647.
[12] SELESNICK I W,BARANIUK R G,KINGSBURY N C.The dual-tree complex wavelet transform[J].IEEE Signal Processing Magazine,2005,22(6):123-151.
[13] SZEGEDY C,VANHOUCKE V,LOFFE S,et al.Rethinking the inception architecture for computer vision[C]//IEEE Conference on Computer Vision and Pattern Recognition.[S.l.]:IEEE,2016:2818-2826.
[14] XIAO J,HAYS J,EHINGER K,et al.Sun database:large-scale scene recognition from abbey to zoo[C]//IEEE Conference on Computer Vision and Pattern Recognition.[S.l.]:IEEE,2010:3485-3492.
[15] TRALIC D,ZUPANCIC I,GRGIC S,et al.CoMo Fod-new database for copy-move forgery detection[C]//IEEE International Symposium Electronics in Marine.[S.l.]:IEEE,2013:49-54.
[16] 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]//ACM International Conference on Multimedia.California:[s.n.],2017:1480-1502.
[17] ZAMPOGLOU M,PAPADOPOULOS S,KOMPATSIARIS Y.Large-scale evaluation of splicing localization algorithms for web images[J].Multimedia Tools and Applications,2017,76(4):4801-4834.

基于双树复数小波四元数卷积网络的Copy-move盲取证算法

Copy-move image blind forgery algorithm based on quaternion convolutional neural networks with dual-tree complex wavelet

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 10

编辑推荐

Metrics

本文评价

[1]	卢鹏丽, 陈云天. 基于网络拓扑和多种生物信息融合的关键蛋白质识别算法[J]. 兰州理工大学学报, 2022, 48(6): 96-103.
[2]	卢鹏丽, 许星舟. 基于精准k核的复杂网络节点重要性评估方法[J]. 兰州理工大学学报, 2022, 48(4): 90-98.
[3]	李策, 许大有, 靳山岗, 高伟哲, 陈晓雷. 基于通道注意力与空洞卷积的胸片肺气肿检测算法[J]. 兰州理工大学学报, 2022, 48(2): 81-89.
[4]	李策, 朱子重, 许大有, 高伟哲, 靳山岗. 基于超复数小波和图像空域的卷积网络融合注视点预测算法[J]. 兰州理工大学学报, 2021, 47(5): 76-84.
[5]	卢鹏丽, 周庚. 基于邻介熵和邻度熵的复杂网络中心性算法[J]. 兰州理工大学学报, 2021, 47(4): 91-98.
[6]	祝延波. 基于图论的中国高铁网节点中心性进化研究[J]. 兰州理工大学学报, 2021, 47(3): 97-104.
[7]	卢鹏丽, 周庚. 基于网络局部和全局特性的组合中心性度量措施[J]. 兰州理工大学学报, 2021, 47(1): 91-96.
[8]	卢鹏丽, 于洲. 基于度与H指数扩展的复杂网络节点排序方法[J]. 兰州理工大学学报, 2020, 46(5): 100-106.
[9]	董瑞洪, 闫厚华, 张秋余, 李学勇. 基于深度森林算法的分布式WSN入侵检测模型[J]. 兰州理工大学学报, 2020, 46(4): 103-109.
[10]	卢鹏丽, 郭旭东, 董璊, 曹乐. 基于介度熵的复杂网络节点重要度识别方法[J]. 兰州理工大学学报, 2020, 46(2): 111-115.