浏览全部资源
扫码关注微信
纸质出版日期： 2024-12-16 ，
移动端阅览
蔺聪， 黄轲， 温雅敏， 卢伟. 2024. 匹配对聚类的图像复制粘贴篡改检测. 中国图象图形学报， 29(12):3595-3611
Lin Cong， Huang Ke， Wen Yamin， Lu Wei. 2024. Image copy-move forgery detection based on the clustering of matched pairs. Journal of Image and Graphics， 29(12):3595-3611
目的
2
图像篡改检测主要分为图像区域复制篡改、图像拼接和对象移除3个方向，其中图像复制粘贴篡改是图像篡改检测的重要研究方向之一。针对目前大多数复制粘贴篡改检测方法难以检测平滑和小的篡改区域，且虚警率较高等问题，提出了一种基于匹配对的密度聚类MP-DBSCAN（matched pairs——density based spatial clustering of applications with noise）和点密度过滤策略的图像复制粘贴篡改检测方法。
方法
2
首先，在图像中提取大量关键点，根据关键点的灰度值分组后进行匹配。其次，提出了一种改进的密度聚类算法MP-DBSCAN，聚类对象为匹配对的一侧，并利用匹配对的另一侧约束聚类过程，即使篡改区域在空间上距离较近，或者篡改区域存在多个的情况，也能把不同的篡改区域较好地区分开来。此外，本文还提出了一种点密度过滤策略，通过删除低密度簇，降低了检测结果的虚警率。最后，通过估计仿射矩阵并使用ZNCC （zero-mean normalized cross-correlation）算法定位篡改区域。
结果
2
消融实验表明了MP-DBSCAN算法和点密度过滤策略的有效性。在FAU、MICC-F600、GRIP和CASIA v2.0这4个数据集上与几个经典的和新颖的检测方法进行了对比实验，本文方法的
F
1
在4个数据集上像素层的实验结果分别是0.914 3、0.890 6、0.939 1和0.856 8。
结论
2
本文提出的MP-DBSCAN聚类算法和点密度过滤策略能有效提高检测算法的性能，即使篡改区域经过旋转、缩放、压缩和添加噪声等处理，本文方法依然能够检测出大部分的篡改区域，性能优于当前的检测算法。
Objective
2
In recent years， with the development of the internet and computer technology， manipulating images and changing their content have become trivial tasks. Therefore， robust image tampering detection methods need to be developed. As passive forensic methods， image forgery methods can be categorized into copy-move， splicing， and inpainting methods. Copy-move involves copying part of the original image to another part of the same image. Many excellent copy-move forgery detection （CMFD） methods have been developed in recent years and can be categorized into block-based， keypoint-based， and deep learning methods. However， these methods have the following drawbacks： 1） they cannot easily detect small or smooth tampered regions； 2） a massive number of features leads to a high computational cost； and 3） false alarm rates are high when the tampered images involve self-similar regions. To solve these issues， a novel CMFD method based on matched pairs， namely， density-based spatial clustering of applications with noise （MP-DBSCAN）， is proposed in this paper along with point density filtering.
Method
2
First， a large number of scale-invariant feature transform （SIFT） keypoints are extracted from the input image by lowering the contrast threshold and normalizing the image scale， thus allowing the detection of a sufficient number of keypoints in small and smooth regions. Second， the generalized two nearest neighbor （G2NN） matching strategy is employed to manage multiple keypoint matching， thus allowing the detection algorithm to perform smoothly even when the tampered region has been copied multiple times. A hierarchical matching strategy is then adopted to solve keypoint matching problems involving a massive number of keypoints. To accelerate the matching process， keypoints are initially grouped by their grayscale values， and then the G2NN matching strategy is applied to each group instead of the keypoints detected from the entire image. The efficiency and accuracy of the matching procedure can be improved without deleting the correct matched pairs. Third， an improved clustering algorithm called MP-DBSCAN is proposed. The matched pairs are grouped into different tampered regions， and the direction of the matched pairs are adjusted before the clustering process. The cluster objects only represent one side of the matched pairs and not all the extracted keypoints， and the keypoints from the other side are used as constraints in the clustering process. A satisfying detection result is obtained even when the tampered regions are close to one another. The proposed method obtains better
F
1
measures compared with the state-of-the-art copy-move
forgery detection methods. Fourth， the prior regions are constructed based on the clustering results. These prior regions can be regarded as the approximate tampered regions. A point density filtering policy is also proposed， where each point density of the region is calculated and the region with the lowest point density is deleted to reduce the false alarm rate. Finally， the tampered regions are located accurately using the affine transforms and the zero-mean normalized cross-correlation （ZNCC） algorithm.
Result
2
The proposed method is compared with the state-of-the-art CMFD methods on four standard datasets， including FAU， MICC-F600， GRIP， and CASIA v2.0. Provided by Christlein， the FAU dataset has an average resolution of about 3 000 × 2 300 pixels and includes tampered images under post-processing operations （e.g.， additional noise and JPEG compression） and various geometrical attacks （e.g.， scaling and rotation）. This dataset involves 48， 480， 384， 432， and 240 plain copy-move， scaling， rotation， JPEG， and noise addition operations， respectively. The MICC-F600 dataset includes images in which a region is duplicated at least once. The resolutions of these images range from 800 × 533 to 3 888 × 2 592 pixels. Among the 600 images in this dataset， 440 are original images and 160 are forged images. The GRIP dataset includes 80 original images and 80 tampered images with a low resolution of 1 024 × 768 pixels. Some tampered regions on these images are very smooth or small. The size of the tampered regions ranges from about 4 000 to 50 000 pixels. The CASIA v2.0 dataset contains 7 491 authentic and 5 123 forged images， of which 1 313 images are forged using copy-move methods. Precision， recall， and
F
1
scores are used as assessment criteria in the experiments. The
F
1
scores of the proposed method on the FAU， MICC-F600， GRIP， and CASIA v2.0 datasets at the pixel level are 0.914 3， 0.890 6， 0.939 1， and 0.856 8， respectively. Extens
ive experimental results demonstrate the superior performance of the proposed method compared with the existing state-of-the-art methods. The effectiveness of the MP-DBSCAN algorithm and the point density filtering policy is also demonstrated via ablation studies.
Conclusion
2
To detect tampered regions accurately， a novel CMFD method based on the MP-DBSCAN algorithm and the point density filtering policy is proposed in this paper. The matched pairs of an image can be divided into different tampered regions by using the MP-DBSCAN algorithm to detect these regions accurately. The mismatched pairs are then discarded by the point density filtering policy to reduce false alarm rates. Extensive experimental results demonstrate that the proposed method exhibits a satisfactory accuracy and robustness compared with the existing state-of-the-art methods.
多媒体取证图像取证图像篡改检测复制粘贴篡改基于密度的带噪声空间聚类（DBSCAN）
multimedia forensicsimage forensicsimage forgery detectioncopy-move forgerydensity based spatial clustering of applications with noise （DBSCAN）
Thakur A and Jindal N. 2021. Copy move and splicing forgery detection using deep convolution neural network， and semantic segmentation. Multimedia Tools and Applications， 80（3）： 3571-3599 ［DOI： 10.1007/s11042-020-09816-3http://dx.doi.org/10.1007/s11042-020-09816-3］
Amerini I， Ballan L， Caldelli R， Del Bimbo A， Del Tongo L and Serra G. 2013. Copy-move forgery detection and localization by means of robust clustering with J-Linkage. Signal Processing： Image Communication， 28（6）： 659-669 ［DOI： 10.1016/j.image.2013.03.006http://dx.doi.org/10.1016/j.image.2013.03.006］
Amerini I， Ballan L， Caldelli R， Del Bimbo A and Serra G. 2011. A sift-based forensic method for copy-move attack detection and transformation recovery. IEEE Transactions on Information Forensics and Security， 6（3）： 1099-1110 ［DOI： 10.1109/TIFS.2011.2129512http://dx.doi.org/10.1109/TIFS.2011.2129512］
Barni M， Phan Q T and Tondi B. 2021. Copy move source-target disambiguation through multi-branch CNNs. IEEE Transactions on Information Forensics and Security， 16： 1825-1840 ［DOI： 10.1109/TIFS.2020.3045903http://dx.doi.org/10.1109/TIFS.2020.3045903］
Bi X L and Pun C M. 2018. Fast copy-move forgery detection using local bidirectional coherency error refinement. Pattern Recognition， 81： 161-175 ［DOI： 10.1016/j.patcog.2018.03.028http://dx.doi.org/10.1016/j.patcog.2018.03.028］
Chen B J， Tan W J， Coatrieux G， Zheng Y H and Shi Y Q. 2021. A serial image copy-move forgery localization scheme with source/target distinguishment. IEEE Transactions on Multimedia， 23： 3506-3517 ［DOI： 10.1109/TMM.2020.3026868http://dx.doi.org/10.1109/TMM.2020.3026868］
Christlein V， Riess C， Jordan J， Riess C and Angelopoulou E. 2012. An evaluation of popular copy-move forgery detection approaches. IEEE Transactions on Information Forensics and Security， 7（6）： 1841-1854 ［DOI： 10.1109/TIFS.2012.2218597http://dx.doi.org/10.1109/TIFS.2012.2218597］
Cozzolino D， Poggi G and Verdoliva L. 2015. Efficient dense-field copy-move forgery detection. IEEE Transactions on Information Forensics and Security， 10（11）： 2284-2297 ［DOI： 10.1109/TIFS.2015.2455334http://dx.doi.org/10.1109/TIFS.2015.2455334］
Dixit A and Bag S. 2021. A fast technique to detect copy-move image forgery with reflection and non-affine transformation attacks. Expert Systems with Applications， 182： #115282 ［DOI： 10.1016/j.eswa.2021.115282http://dx.doi.org/10.1016/j.eswa.2021.115282］
Emam M， Han Q and Niu X M. 2016. PCET based copy-move forgery detection in images under geometric transforms. Multimedia Tools and Applications， 75（18）： 11513-11527 ［DOI： 10.1007/s11042-015-2872-2http://dx.doi.org/10.1007/s11042-015-2872-2］
Fischler M A and Bolles R C. 1981. Random sample consensus： a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM， 24（6）： 381-395 ［DOI： 10.1145/358669.358692http://dx.doi.org/10.1145/358669.358692］
Fridrich A J， Soukal B D and Lukáš A J. 2003. Detection of copy-move forgery in digital images//Proceedings of Digital Forensic Research Workshop. Cleveland， OH， USA： 19-23
Gan Y F， Zhong J L and Vong C. 2022. A novel copy-move forgery detection algorithm via feature label matching and hierarchical segmentation filtering. Information Processing and Management， 59（1）： #102783 ［DOI： 10.1016/j.ipm.2021.102783http://dx.doi.org/10.1016/j.ipm.2021.102783］
Lai Y C， Huang T Q and Jiang R X. 2015. Image region copy-move forgery detection based on Exponential-Fourier moments. Journal of Image and Graphics， 20（9）： 1212-1221
赖玥聪， 黄添强， 蒋仁祥. 2015. 采用指数矩的图像区域复制粘贴篡改检测. 中国图象图形学报， 20（9）： 1212-1221 ［DOI： 10.11834/jig.20150908http://dx.doi.org/10.11834/jig.20150908］
Li J， Li X L， Yang B and Sun X M. 2015. Segmentation-based image copy-move forgery detection scheme. IEEE Transactions on Information Forensics and Security， 10（3）： 507-518 ［DOI： 10.1109/TIFS.2014.2381872http://dx.doi.org/10.1109/TIFS.2014.2381872］
Li X L， Yu N H， Zhang X P， Zhang W M， Li B， Lu W， Wang W and Liu X L. 2021. Overview of digital media forensics technology. Journal of Image and Graphics， 26（6）： 1216-1226
李晓龙， 俞能海， 张新鹏， 张卫明， 李斌， 卢伟， 王伟， 刘晓龙. 2021. 数字媒体取证技术综述. 中国图象图形学报， 26（6）： 1216-1226 ［DOI： 10.11834/jig.210081http://dx.doi.org/10.11834/jig.210081］
Li Y M and Zhou J T. 2019. Fast and effective image copy-move forgery detection via hierarchical feature point matching. IEEE Transactions on Information Forensics and Security， 14（5）： 1307-1322 ［DOI： 10.1109/TIFS.2018.2876837http://dx.doi.org/10.1109/TIFS.2018.2876837］
Li Y N. 2013. Image copy-move forgery detection based on polar cosine transform and approximate nearest neighbor searching. Forensic Science International， 224（1/3）： 59-67 ［DOI： 10.1016/j.forsciint.2012.10.031http://dx.doi.org/10.1016/j.forsciint.2012.10.031］
Lin C， Lu W， Huang X C， Liu K， Sun W and Lin H H. 2019. Region duplication detection based on hybrid feature and evaluative clustering. Multimedia Tools and Applications， 78（15）： 20739-20763 ［DOI： 10.1007/s11042-019-7342-9http://dx.doi.org/10.1007/s11042-019-7342-9］
Lin C， Lu W， Sun W， Zeng J H， Xu T H and Lai J H. 2018. Region duplication detection based on image segmentation and keypoint contexts. Multimedia Tools and Applications， 77（11）： 14241-14258 ［DOI： 10.1007/s11042-017-5027-9http://dx.doi.org/10.1007/s11042-017-5027-9］
Liu B and Pun C M. 2018. Locating splicing forgery by fully convolutional networks and conditional random field. Signal Processing： Image Communication， 66： 103-112 ［DOI： 10.1016/j.image.2018.04.011http://dx.doi.org/10.1016/j.image.2018.04.011］
Liu L Y， Wang J X， Cao S L， Zhao L and Zhang X Q. 2022. U-Net for detecting small forgery region. Journal of Image and Graphics， 27（1）： 176-187
刘丽颖， 王金鑫， 曹少丽， 赵丽， 张笑钦. 2022. 检测小篡改区域的U型网络. 中国图象图形学报， 27（1）： 176-187 ［DOI： 10.11834/jig.210438http://dx.doi.org/10.11834/jig.210438］
Liu Y Q， Xia C， Zhu X B and Xu S W. 2022. Two-stage copy-move forgery detection with self deep matching and proposal SuperGlue. IEEE Transactions on Image Processing， 31： 541-555 ［DOI： 10.1109/TIP.2021.3132828http://dx.doi.org/10.1109/TIP.2021.3132828］
Lowe D G. 2004. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision， 60（2）： 91-110 ［DOI： 10.1023/B：VISI.0000029664.99615.94http://dx.doi.org/10.1023/B：VISI.0000029664.99615.94］
Lyu Q Y， Luo J W， Liu K， Yin X L， Liu J R and Lu W. 2021. Copy Move Forgery Detection based on double matching. Journal of Visual Communication and Image Representation， 76： #103057 ［DOI： 10.1016/j.jvcir.2021.103057http://dx.doi.org/10.1016/j.jvcir.2021.103057］
Mahdian B and Saic S. 2007. Detection of copy-move forgery using a method based on blur moment invariants. Forensic Science International， 171（2/3）： 180-189 ［DOI： 10.1016/j.forsciint.2006.11.002http://dx.doi.org/10.1016/j.forsciint.2006.11.002］
Muhammad G， Hussain M and Bebis G. 2012. Passive copy move image forgery detection using undecimated dyadic wavelet transform. Digital Investigation， 9（1）： 49-57 ［DOI： 10.1016/j.diin.2012.04.004http://dx.doi.org/10.1016/j.diin.2012.04.004］
Nazir T， Nawaz M， Masood M and Javed A. 2022. Copy move forgery detection and segmentation using improved mask region-based convolution network （RCNN）. Applied Soft Computing， 131： #109778 ［DOI： 10.1016/j.asoc.2022.109778http://dx.doi.org/10.1016/j.asoc.2022.109778］
Niu P， Wang C， Chen W， Yang H and Wang X. 2021. Fast and effective keypoint-based image copy-move forgery detection using complex-valued moment invariants. Journal of Visual Communication and Image Representation， 77： #103068 ［DOI： 10.1016/j.jvcir.2021.103068http://dx.doi.org/10.1016/j.jvcir.2021.103068］
Pan X Y and Lyu S W. 2010. Region duplication detection using image feature matching. IEEE Transactions on Information Forensics and Security， 5（4）： 857-867 ［DOI： 10.1109/TIFS.2010.2078506http://dx.doi.org/10.1109/TIFS.2010.2078506］
Qin J， Li F， Xiang L Y and Yin C M. 2013. Detection of image region copy-move forgery using radial harmonic Fourier moments. Journal of Image and Graphics， 18（8）： 919-923
秦娟， 李峰， 向凌云， 殷苌茗. 2013. 采用圆谐—傅里叶矩的图像区域复制粘贴篡改检测. 中国图象图形学报， 18（8）： 919-923 ［DOI： 10.11834/jig.20130805http://dx.doi.org/10.11834/jig.20130805］
Rao Y and Ni J Q. 2016. A deep learning approach to detection of splicing and copy-move forgeries in images//2016 IEEE International Workshop on Information Forensics and Security （WIFS）. Abu Dhabi， United Arab Emirates： IEEE： 1-6 ［DOI： 10.1109/WIFS.2016.7823911http://dx.doi.org/10.1109/WIFS.2016.7823911］
Ryu S J， Kirchner M， Lee M J and Lee H K. 2013. Rotation invariant localization of duplicated image regions based on Zernike moments. IEEE Transactions on Information Forensics and Security， 8（8）： 1355-1370 ［DOI： 10.1109/TIFS.2013.2272377http://dx.doi.org/10.1109/TIFS.2013.2272377］
Silva E， Carvalho T， Ferreira A and Rocha A. 2015. Going deeper into copy-move forgery detection： exploring image telltales via multi-scale analysis and voting processes. Journal of Visual Communication and Image Representation， 29： 16-32 ［DOI： 10.1016/j.jvcir.2015.01.016http://dx.doi.org/10.1016/j.jvcir.2015.01.016］
Wang C， Huang Z Q， Qi S R， Yu Y S， Shen G H and Zhang Y S. 2023. Shrinking the semantic gap： spatial pooling of local moment invariants for copy-move forgery detection. IEEE Transactions on Information Forensics and Security， 18： 1064-1079 ［DOI： 10.1109/TIFS.2023.3234861http://dx.doi.org/10.1109/TIFS.2023.3234861］
Wang X Y， Chen W C， Niu P P and Yang H Y. 2022. Image copy-move forgery detection based on dynamic threshold with dense points. Journal of Visual Communication and Image Representation， 89： #103658 ［DOI： 10.1016/j.jvcir.2022.103658http://dx.doi.org/10.1016/j.jvcir.2022.103658］
Wang X Y， Li S， Liu Y N， Niu Y， Yang H Y and Zhou Z L. 2017. A new keypoint-based copy-move forgery detection for small smooth regions. Multimedia Tools and Applications， 76（22）： 23353-23382 ［DOI： 10.1007/s11042-016-4140-5http://dx.doi.org/10.1007/s11042-016-4140-5］
Wang X Y， Wang X Q， Niu P P and Yang H Y. 2024. Accurate and robust image copy-move forgery detection using adaptive keypoints and FQGPCET-GLCM feature. Multimedia Tools and Applications， 83（1）： 2203-2235 ［DOI： 10.1007/s11042-023-15499-3http://dx.doi.org/10.1007/s11042-023-15499-3］
Weng S W， Zhu T G， Zhang T C and Zhang C Y. 2024. UCM-Net： a U-Net-like tampered-region-related framework for copy-move forgery detection. IEEE Transactions on Multimedia， 26： 750-763 ［DOI： 10.1109/TMM.2023.3270629http://dx.doi.org/10.1109/TMM.2023.3270629］
Wu Y， Abd-Almageed W and Natarajan P. 2018. BusterNet： detecting copy-move image forgery with source/target localization//Proceedings of the 15th European Conference on Computer Vision. Munich， Germany： Springer： 170-186 ［DOI： 10.1007/978-3-030-01231-1_11http://dx.doi.org/10.1007/978-3-030-01231-1_11］
Yang F， Li J W， Lu W and Weng J. 2017. Copy-move forgery detection based on hybrid features. Engineering Applications of Artificial Intelligence， 59： 73-83 ［DOI： 10.1016/j.engappai.2016.12.022http://dx.doi.org/10.1016/j.engappai.2016.12.022］
Zandi M， Mahmoudi-Aznaveh A and Talebpour A. 2016. Iterative copy-move forgery detection based on a new interest point detector. IEEE Transactions on Information Forensics and Security， 11（11）： 2499-2512 ［DOI： 10.1109/TIFS.2016.2585118http://dx.doi.org/10.1109/TIFS.2016.2585118］
Zhang Y L， Zhu G P， Wang X， Luo X Y， Zhou Y C， Zhang H L and Wu L G. 2023. CNN-Transformer based generative adversarial network for copy-move source/target distinguishment. IEEE Transactions on Circuits and Systems for Video Technology， 33（5）： 2019-2032 ［DOI： 10.1109/TCSVT.2022.3220630http://dx.doi.org/10.1109/TCSVT.2022.3220630］
Zhong J L and Pun C M. 2020. An end-to-end dense-InceptionNet for image copy-move forgery detection. IEEE Transactions on Information Forensics and Security， 15： 2134-2146 ［DOI： 10.1109/TIFS.2019.2957693http://dx.doi.org/10.1109/TIFS.2019.2957693］
Zhu Y， Chen C F， Yan G， Guo Y C and Dong Y F. 2020. AR-Net： adaptive attention and residual refinement network for copy-move forgery detection. IEEE Transactions on Industrial Informatics， 16（10）： 6714-6723 ［DOI： 10.1109/TII.2020.2982705http://dx.doi.org/10.1109/TII.2020.2982705］
Zhu Y， Yu Y L and Guo Y C. 2022. HRDA-Net： image multiple manipulation detection and location algorithm in real scene. Journal on Communications， 43（1）： 217-226
朱叶， 余宜林， 郭迎春. 2022. HRDA-Net： 面向真实场景的图像多篡改检测与定位算法. 通信学报， 43（1）： 217-226 ［DOI： 10.11959/j.issn.1000-436x.2022016http://dx.doi.org/10.11959/j.issn.1000-436x.2022016］
相关作者
相关机构
京公网安备11010802024621