Hibrit sinir ağı yaklaşımı ile kopyala-taşı sahteciliği tespiti ve lokalizasyonu

Öz

Görüntünün bir kısmının kopyalayıp aynı görüntü üzerinde başka bir bölgeye bölge gizlemek veya çoğaltmak amacıyla yapıştırılarak oluşturulan kopya-taşı sahteciliği, son yıllarda en çok karşılaşılan görüntü sahteciliği tekniğidir. Literatürde bu tür sahtecilikleri tespit etmek için birçok çalışma önerilmiştir. Bu yaklaşımların ana dezavantajı, sahte görüntü bazı işleme öncesi veya sonrası saldırılara maruz kaldığında performanslarının düşebilmesidir. Bu çalışmada, derin öznitelikler ile DCT tabanlı blok özniteliklerinin bir arada kullanıldığı hibrit bir yaklaşım ile çeşitli saldırı senaryolarında dahi daha iyi tespit oranlarının elde edilmesi amaçlanmaktadır. Önerilen yöntem, ön işleme aşamasında LDR adı verilen global bir kontrast düzeltme tekniği kullanır ve daha sonra derin bir sinir ağı kullanarak görüntü yamalarından derin öznitelikler çıkarır. Yöntem ayrıca, yöntemi JPEG sıkıştırma saldırılarına karşı daha sağlam hale getirmek için görüntüden blok özellikleri alır. Hibrit özellikler (derin ve blok tabanlı özellikler) Yama Eşleştirme kullanılarak eşleştirilir ve ardından yanlış eşleşmeleri en aza indirmek için eşleştirme sonuçları üzerinde önerilen son işleme işlemi gerçekleştirilir. Mevcut veri tabanları üzerinde gerçekleştirilen deneysel çalışmalara göre önerilen şema, yüksek oranda parametrelerle yapılan saldırılar altında bile hem anahtar nokta tabanlı hem de blok tabanlı referanslara kıyasla daha iyi sonuçlar vermektedir.

Anahtar Kelimeler

• Kopyala-taşı sahteciliği
• Derin öznitelikler
• Hibrit öznitelikler
• Yama tabanlı eşleşeme

Copy-Move forgery detection and localization with hybrid neural network approach

Abstract

Copy-move forgery, in which copied a region of the image and pasted onto another region on the same image, is the most encountered image forgery technique recently. Many frameworks have been presented to detect such forgeries. The main drawback with these approaches is their performance can be degraded when the duplicated image has undergone to some attacks. In this work, it is aimed to propose a hybrid approach, which uses deep features and DCT-based block features in a combined manner, to achieve higher detection performance even if under various attack scenarios. The proposed method uses a global contrast correction technique called LDR during the preprocessing phase and then extracts deep features from the image patches using a deep neural network. The method also obtains block features from the image to robustness against JPEG compression attacks. Hybrid features (deep and block-based features) are matched using Patch Match and then the proposed post-processing operation is realized on the matching results to minimize false matches. According to empirical studies performed on available databases, the proposed scheme gives better results when compared to both keypoint-based and block-based references even under attacks with challenging parameters.

Keywords

• Copy-move forgery
• Deep based features
• Hybrid features
• Patch based matching

Kaynakça

1. [1] Lian S, Kanellopoulos D. “Recent advances in multimedia information system security”. Informatica, 33, 3-24, 2009.
2. [2] Fridrich A, Soukal JBD, Lukáš AJ. “Detection of copy-move forgery in digital images”. Digital Forensic Research Workshop, Ohio, ABD, 6-8 August, 2003.
3. [3] Popescu A, Farid H. “Exposing Digital Forgeries by Detecting Duplicated Image Regions”. Computer Science Technical Report TR2004-515, 2004.
4. [4] Mahdian B, Saic S. “Detection of copy-move forgery using a method based on blur moment invariants”. Forensic Science International, 171(2-3), 180-189, 2007.
5. [5] Bayram S, Sencar HT, Memon N. “An efficient and robust method for detecting copy-move forgery”. IEEE International Conference on Acoustics, Speech and Signal Processing, New York, USA, 19-24 April 2009.
6. [6] Luo W, Huang, J, Qiu, G. “Robust detection of region-duplication forgery in digital images”. International Conference on Pattern Recognition, Hong Kong, China, 20-24 August 2009.
7. [7] Wang J, Liu G, Li H, Dai Y, Wang Z. “Detection of image region duplication forgery using model with circle block”. 1st International Conference on Multimedia Information Networking and Security, Hubei, China, November 2009.
8. [8] Bravo-Solorio, S, Nandi, AK. “Exposing duplicated regions affected by reflection, rotation and scaling”. International Conference on Acoustics, Speech and Signal Processing, Prague, Czech Republic, 22-27 May 2011.

9. [9] Wu Q, Wang S, Zhang X. "Log-Polar based scheme for revealing duplicated regions in digital images". IEEE Signal Processing Letters, 18(10), 559-562, 2011.
10. [10] Li L, Li S, Zhu H. “An efficient scheme for detecting copymove forged images by local binary patterns”. Journal of Information Hiding and Multimedia Signal Processing, 4(1), 46-56, 2013.
11. [11] Ryu S, Kirchner M, Lee M, Lee H. “Rotation invariant localization of duplicated image regions based on zernike moments”. IEEE Transaction on Information Forensics and Security, 8(8), 1355-1370, 2013.
12. [12] Cozzolino D, Poggi G, Verdoliva L. “Efficient dense-field copy-move forgery detection”. IEEE Transactions on Information Forensics and Security, 10(11), 2284-2297, 2015.
13. [13] Bi X, Pun C, Yuan X. “Multi-level dense descriptor and hierarchical feature matching for copy-move forgery detection”. Information Sciences, 345, 226-242, 2016.
14. [14] Emam M, Han Q, Niu X, “PCET based copy-move forgery detection in images under geometric transforms”. Multimedia Tools and Applications, 75(18), 11513-11527, 2016.
15. [15] Bi X, Pun CM. “Fast reflective offset-guided searching method for copy-move forgery detection”. Information Sciences, 418-419, 531-545, 2017.
16. [16] Bi X, Pun CM. “Fast copy-move forgery detection using local bidirectional coherency error refinement”. Pattern Recognition, 81, 161-175, 2018.
17. [17] Huang H, Guo W, Zhang Y. “Detection of copy-move forgery in digital images using SIFT algorithm”. IEEE Pacific-Asia Workshop on Computational Intelligent and Industrial Application, Wuhan, China, 19-20 December 2008.
18. [18] Amerini I, Ballan L, Caldelli R, Bimbo AD, Serra G. “A SIFT-based forensic method for copy-move attack detection and transformation recovery”. IEEE Transactions on Information Forensics and Security, 6(3), 1099-1110, 2011.
19. [19] Amerini I, Ballan L, Caldelli R, Bimbo AD, Del Tongo L, Serra G. “Copy-move forgery detection and localization by means of robust clustering with J-linkage”. Signal Processing: Image Communication, 28(6), 659-1669, 2013.
20. [20] Bo X, Junwen W, Guangjie L, Yuewei D. "Image copy-move forgery detection based on SURF". International Conference on Multimedia Information Networking and Security, Nanjing, China, 4-6 November 2010.
21. [21] Christlein V, Riess C, Jordan J, Riess C, Angelopoulou E. "An evaluation of popular copy-move forgery detection approaches". IEEE Transactions on Information Forensics and Security, 7, 1841-1854, 2012.
22. [22] Zhu Y, Shen X, Chen H. “Copy-Move Forgery Detection Based on Scaled ORB”. Multimedia Tools and Applications, 75(6) 1-15, 2015.
23. [23] Li J, Li X, Yang B. “Segmentation-based image copy-move forgery detection scheme”. IEEE Transactions on Information Forensics and Security, 10(3), 507-518, 2015.
24. [24] Pun CM, Yuan XC, Li X. “Forgery detection using adaptive oversegmentation and feature point matching”. IEEE Transactions on Information Forensics and Security, 10 (8), 1705-1716, 2015.
25. [25] Wenchang S, Fei Z, Bo Q, Bin L. “Improving image copymove forgery detection with particle swarm optimization techniques”. China Communications, 13(1), 139-149, 2016.
26. [26] Zandi M, Mahmoudi-Aznaveh A, Talebpour A. “Iterative copy-move forgery detection based on a new interest point detector”. Transactions on Information Forensics and Security, 11(11), 2499-2512, 2016.
27. [27] Yang F, Li J, Lu W, Weng J. “Copy-Move forgery detection based on hybrid features”. Engineering Applications of Artificial Intelligence, 59, 73-83, 2017.
28. [28] Li Y, Zhou J. “Image copy-move forgery detection using hierarchical feature point matching”. 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA), Jeju, Korea (South), 13-16 December 2016
29. [29] Rao Y, Ni J. "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, 4-7 December 2016.
30. [30] Ouyang J, Liu Y, Liao M. “Copy-move forgery detection based on deep learning”. 2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), Shanghai, China, 14-16 October 2017.
31. [31] Yue W, Abd-Almageed W, Natarajan P. “Image copy-move forgery detection via an end-to-end deep neural network”. 2018 IEEE Winter Conference on Applications of Computer Vision, Lake Tahoe, NV, USA, 12-15 March 2018.
32. [32] Cozzolino D, Poggi G, Verdoliva L. “Copy-move forgery detection based on PatchMatch”. 2014 IEEE International Conference on Image Processing (ICIP), Paris, France, 27-30 October 2014.
33. [33] Simonyan K, Zisserman A. “Very deep convolutional networks for large-scale image recognition”. International Conference on Learning Representations, San Diego, CA, 10 April 2015.
34. [34] Lee C, Kim C. “Contrast enhancement based on layered difference representation”. IEEE Transactions on Image Processing, 22(12), 5372-5384, 2013.
35. [35] Li Q, Cai W, Wang X, Zhou Y, Feng DD, Chen M. “Medical image classification with convolutional neural network”. 13th International Conference on Control Automation Robotics & Vision (ICARCV), Singapore, 10-12 December 2014.
36. [36] Song X, Feng F, Liu J, Li Z, Nie L, Ma J. “Neurostylist: neural compatibility modeling for clothing matching”. 25th ACM International Conference on Multimedia, New York, United States, 23-27 October 2017.
37. [37] Wu JD, Ye SH. “Driver identification using finger-vein patterns with Radon transform and neural network”. Expert Systems and Application, 36(3), 5793-5799, 2009.
38. [38] Erhan D, Szegedy C, Toshev A, Anguelov D. “Scalable object detection using deep neural networks”. Computer Vision Pattern Recognation (CVPR), 2013. https://doi.org/10.48550/arXiv.1312.2249
39. [39] Sermanet P, Eigen D, Zhang X, Mathieu M, Fergus R, LeCun Y. “Overfeat: Integrated recognition, localization and detection using convolutional networks”. Computer Vision and Pattern Recognition, 2014. https://doi.org/10.48550/arXiv.1312.6229
40. [40] Krizhevsky A, Sutskever I, Geoffrey A, Hinton E. "ImageNet Classification with Deep Convolutional Neural Networks". Advances in Neural Information Processing Systems, 2012. https://doi.org/10.48550/arXiv.1409.0575
41. [41] Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov, D, Erhan D, Vanhoucke V, Rabinovich A. "Going Deeper with Convolutions". 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 7-12 June 2015.
42. [42] Jia D, Wei D, Richard S, Li-Jia L, Kai L, Li FF. “Imagenet: A large-scale hierarchical image database”. 2009 IEEE Conference on Computer Vision and Pattern Recognition CVPR 2009, Miami, FL, USA, 20-25 June 2009.
43. [43] Sermanet P, Eigen D, Zhangm X, Mathieu M, Fergus R, LeCun Y. “Overfeat: Integrated recognition, localization and detection using convolutional networks”. Computer Vision and Pattern Recognition, 2014. https://doi.org/10.48550/arXiv.1312.6229
44. [44] Russakovsky O, Deng J, Su H. "ImageNet Large Scale Visual Recognition Challenge". Computer Vision and Pattern Recognition, 2015. https://doi.org/10.48550/arXiv.1409.0575
45. [45] Barnes C, Shechtman E, Finkelstein A, Goldman DB. “PatchMatch: a randomized correspondence algorithm for structural image editing”. ACM Transactions on Graphics, 28(3), 1-11, 2009.
46. [46] Fischler MA, Bolles RC. “Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography”. Communications of the ACM, 24(6), 381-395, 1981.
47. [47] Christlein V, Riess C, Angelopoulou E. “On rotation invariance in copy-move forgery detection”. IEEE International Workshop Information Forensics Security, Seattle, WA, USA, 12-15 December 2010.
48. [48] Ulutas G, Ustubıoglu B, Ulutas M, Nabıyev V. "Video forgery detection method based on local difference binary". Pamukkale University Journal of Engineering Sciences, 26(5), 983-992, 2020.
49. [49] Yang HY, Qi SR, Niu Y, Niu PP, Wang XY. “Copy-Move forgery detection based on adaptive keypoints extraction and matching”. Multimedia Tools and Application, 78(24), 34585-34612, 2019.
50. [50] Li Y, Zhou J. “Fast and effective image copy-move forgery detection via hierarchical feature point matching”. IEEE Transactions and Information Forensics Securuty, 14(5), 1-16, 2019.
51. [51] Meena KB, Tyagi V. “A copy-move image forgery detection technique based on tetrolet transform”. Journal of Information Security and Applications, 2020. https://doi.org/10.1016/j.jisa.2020.102481
52. [52] Wang Y, Kang X, Chen Y. “Robust and accurate detection of image copy-move forgery using PCET-SVD and histogram of block similarity measures”. Journal of Information Security and Applications, 2020. https://doi.org/10.1016/j.jisa.2020.102536
53. [53] Tahaoglu G, Ulutas G, Ustubioglu B, Nabiyev V. “Improved copy-move forgery detection method via L*a*b* color space and enhanced localization technique”. Multimedia Tools Application, 80, 23419-23456, 2021.
54. [54] Rodriguez-Ortega Y, Ballesteros DM, Renza D. “CopyMove forgery detection (CMFD) using deep learning for image and video forensics”. Journal of Imaging, 2021. https://doi.org/10.3390/jimaging7030059.