Copy-move Forgeries Detection Based on Polar Sine Transform
-
摘要:
该文使用极坐标正弦变换(PST)特征对图像进行Copy-move篡改检测,将待检测图像转换成灰度图并进行PST特征提取,并采用改进的快速近似最近邻搜索算法PatchMatch对特征描述符进行匹配,以克服匹配全局描述符带来的处理时间较长的缺点。实验分析表明,该文所提方法不仅对图像的线性Copy-move篡改和旋转干扰篡改有很好的效果,而且对噪声和JPEG压缩干扰篡改也具有一定的鲁棒性。最后对综合干扰篡改实验测试发现,在综合篡改幅度较小的情况下,准确率可以达到98.0%。
-
关键词:
- 图像检测 /
- 图像篡改 /
- 极坐标正弦变换 /
- PatchMatch
Abstract:Polar Sine Transform (PST) is used to detect Copy-move forgeries in the paper, and the image to be detected is transformed into gray scale image and feature extraction is carried out by PST. Improved PatchMatch, a fast approximate nearest neighbor search algorithm, is used to match feature descriptors to overcome the problem of long time consuming caused by matching global descriptors. Experiments show that the proposed method is not only effective for linear Copy-move forgeries and rotation interference forgeries, but also robust to noise and JPEG compression interference forgeries. Finally, the experimental results of synthetic interference forgeries show that the accuracy can reach 98.0% when the synthetic forgeries range is small.
-
Key words:
- Image detection /
- Image forgery /
- Polar Sine Transform (PST) /
- PatchMatch
-
AL-QERSHI O M and KHOO B E. Passive detection of copy-move forgery in digital images: State-of-the-art[J]. Forensic Science International, 2013, 231(1/3): 284–295. doi: 10.1016/j.forsciint.2013.05.027 ZHOU Xinmin, WANG Kaiyuan, and FU Jian. A method of SIFT simplifying and matching algorithm improvement[C]. IEEE 2016 International Conference on Industrial Informatics - Computing Technology, Intelligent Technology, Industrial Information Integration (ICIICII), Wuhan, China, 2016: 73–77. doi: 10.1109/ICIICII.2016.0029. AHSAN A M and MOHAMAD D B. Machine learning technique for object detection based on SURF feature[J]. International Journal of Computational Vision and Robotics, 2017, 7(1/2): 6–19. doi: 10.1504/IJCVR.2017.081232 FARID H. Image forgery detection[J]. IEEE Signal Processing Magazine, 2009, 26(2): 16–25. doi: 10.1109/MSP.2008.931079 PIVA A. An overview on image forensics[J]. ISRN Signal Processing, 2013, 2013: 496701. AL-QERSHI O M and KHOO B E. Enhanced matching method for copy-move forgery detection by means of Zernike moments[C]. The 13th International Workshop on Digital-Forensics and Watermarking, Taipei, China, 2014: 485–497. doi: 10.1007/978-3-319-19321-2_37. 闫旭, 姜威, 贲晛烨. 基于改进Hu不变矩的图像篡改检测算法[J]. 光学技术, 2018, 44(2): 171–176. doi: 10.13741/j.cnki.11-1879/o4.2018.02.008YAN Xu, JIANG Wei, and BEN Xianye. Image tamper detection algorithm based on improved Hu invariant moments[J]. Optical Technique, 2018, 44(2): 171–176. doi: 10.13741/j.cnki.11-1879/o4.2018.02.008 AMERINI I, BALLAN L, CALDELLI R, et al. A SIFT-based forensic method for copy–move attack detection and transformation recovery[J]. IEEE Transactions on Information Forensics and Security, 2011, 6(3): 1099–1110. doi: 10.1109/TIFS.2011.2129512 MUHAMMAD G, HUSSAIN M, KHAWAJI K, et al. Blind copy move image forgery detection using dyadic undecimated wavelet transform[C]. The 17th IEEE International Conference on Digital Signal Processing, Corfu, Greece, 2011. doi: 10.1109/ICDSP.2011.6004974. 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. doi: 10.1109/TIFS.2012.2218597 YAP P T, JIANG Xudong, and KOT A C. Two-dimensional polar harmonic transforms for invariant image representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(7): 1259–1270. doi: 10.1109/TPAMI.2009.119 李扬, 吴敏渊, 颜佳. 基于改进PatchMatch的自相似性图像超分辨率算法[J]. 计算机应用研究, 2018, 35(4): 1231–1235. doi: 10.3969/j.issn.1001-3695.2018.04.058LI Yang, WU Minyuan, and YAN Jia. Self-similarity based image super-resolution algorithm using optimized PatchMatch[J]. Application Research of Computers, 2018, 35(4): 1231–1235. doi: 10.3969/j.issn.1001-3695.2018.04.058 BARNES C, SHECHTMAN E, FINKELSTEIN A, et al. PatchMatch: A randomized correspondence algorithm for structural image editing[J]. ACM Transactions on Graphics, 2009, 28(3): No. 24. doi: 10.1145/1531326.1531330 BARNES C, SHECHTMAN E, GOLDMAN D B, et al. The generalized PatchMatch correspondence algorithm[C]. The 11th European Conference on Computer Vision–ECCV 2010, Heraklion, Greece, 2010: 29–43. doi: 10.1007/978-3-642-15558-1_3. COZZOLINO D, POGGI G, and VERDOLIVA L. Efficient dense-field Copy-move forgery detection[J]. IEEE Transactions on Information Forensics and Security, 2015, 10(11): 2284–2297. doi: 10.1109/TIFS.2015.2455334 EHRET T and ARIAS P. On the convergence of PatchMatch and its variants[C]. 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, USA, 2018: 1121–1129. doi: 10.1109/CVPR.2018.00123. EHRET T. Automatic detection of internal copy-move forgeries in images[J]. Image Processing on Line, 2018(8): 167–191. doi: 10.5201/ipol.2018.213