Please use this identifier to cite or link to this item:
標題: 使用SIFT特徵之強健數位影像浮水印
Digital image watermarking robust against geometric distortions using SIFT features
作者: 趙秉岐
Chao, Ping-chi
關鍵字: watermark
feature point
geometric distortion
出版社: 資訊科學與工程學系所
引用: [1] C. Tang and H. Hang, “A Feature-Based Robust Digital Image Watermarking Scheme,” IEEE Transactions On Signal Processing, vol. 51, no. 4, April 2003. [2] H. Lee, H. Kim and H. Lee, “Robust image watermarking using local invariant features,” Optical Engineering, 45(3), 037002, March 2006. [3] D. G. Lowe, “Distinctive Image Features From Scale-Invariant Keypoints,” Int. J. Computer Vision. 60(2), 91-110, 2004. [4] I. Cox, J. Kilian, T. Leighton, and T. Shamoon, “Secure Spread Spectrum Watermarking for Images, Audio, and Video,” NEC Res. Inst., Princeton, NJ, Tech. Rep. 95-10, 1995. [5] C.T. Hsu and J. L. Wu, “Hidden Digital Watermarks in Images,” IEEE Transactions on Image Processing, vol. 8, January 1999, pp. 58-68. [6] C.S. Tsai, C. C. Chang, T. S. Chen, and M. E. Chen, “Embedding Robust Gray-level Watermarks in An Image Using Discrete Cosine Transformation,” to appear in Distributed Multimedia Database: Techniques and Applications. [7] C. Harris and M.J. Stephens, “A Combined Corner and Edge Detector,” In Alvey Vision Conference, 1988, pp. 147-152. [8] H. Moravec, “Obstacle Avoidance and Navigation in The Real World by A Seeing Robot Rover,” Technical Report CMU-RI-TR-3, Carnegie-Mellon University, Robotics Institute, 1980. [9] K. Mikolajczyk and C. Schmid, “A Performance Evaluation of Local Descriptors,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, no. 10, October 2005. [10] H. Bay, T. Tuytelaars, and L. V. Gool, “SURF: Speeded Up Robust Features,” Proceedings of the ninth European Conference on Computer Vision, May 2006. [11] Fabien A. P. Petitcolas, Ross J. Anderson, Markus G. Kuhn. Attacks on copyright marking systems, in David Aucsmith (Ed), Information Hiding, Second International Workshop, IH'98, Portland, Oregon, U.S.A., April 15-17, 1998, Proceedings, LNCS 1525, Springer-Verlag, ISBN 3-540-65386-4, pp. 219-239. [12] Fabien A. P. Petitcolas. Watermarking schemes evaluation. I.E.E.E. Signal Processing, vol. 17, no. 5, pp. 58-64, September 2000. [13] Alghoniemy, M. and Tewfik, A. H., “Geometric distortion correction through image normalization,” IEEE International Conference on Multimedia and Expo. New York, NY, USA, 2000, vol. 3, pp. 1291-1294. [14] Shen, D. and Ip, H. H. S., “Generalized affine invariant image normalization,” IEEE Transactions on Pattern Analysis and Machine Intelligence. 1997, vol. 19(5), pp. 431-440. [15] Alatter, A. M. and Meyer, J., “Watermark re-synchronization using log-polar mapping of image autocorrelation,” Proceedings of the 2003 International Symposium on Circuits and System, 2003, vol. 2, pp. 928-931. [16] Solachidis, V. and Pitas, I., “Self-similar ring shaped watermark embedding in 2-D DFT domain,” European Signal Processing Conference, 2000, vol. 4, pp. 1977-1980. [17] Lin, C. Y., Wu, M., Bloom, J. A., Cox, I. J., Miller, M. L. and Lui, Y. M., “Rotation, scale, and translation resilient watermarking for images,” IEEE Transactions on Image Processing. 2001, vol. 10(5), pp. 767-782.
摘要: 幾何變形對許多的浮水印技術都是一個難以抵抗的破壞,而近年來發展了不少方法專門抵抗幾何變形破壞。其中利用特徵點為基礎所建立的浮水印技術,效果特別突出。本論文提出了一個利用Lowe所提出的SIFT特徵點粹取,作為基礎的強健浮水印方法,以往有很多浮水印的方法沒辦法抵抗幾何變形的破壞,因為當圖片在受到幾何變形的破壞之後,便沒辦法再用原本的方式找出藏入浮水印的位置。而我們提出了的這個方法對於幾何變形破壞有著足夠的抵抗能力。藉由SIFT特徵點,其所具有的旋轉、轉換與尺度不變性,實現了在幾何變形破壞之後,依然能找出原本藏入浮水印位置的可能。這也是我們依賴SIFT當作藏入參考位置的原因。同時,這個方法在取出浮水印時,不需要使用到未藏入浮水印圖片,這使得本方法的應用性更為增加。
This thesis describes a robust watermarking method for digital images using local invariant features. There are a lot of watermarking algorithms which are unable to resist geometric distortions in past. Because they can not extracts the location where the watermarking information inserted. We propose a watermarking method that is robust to geometric distortions. We use a local invariant feature of the image called the scale-invariant feature transform (SIFT) to resist geometric distortions. SIFT is invariant to translation and scaling distortions. That is why we inserts watermark to rectangle windows by the SIFT. Our method belongs to the blind watermark, because we do not need the original image during detection. We have performed some simulation to show the robustness of the proposed method. The simulation results support the contention that our method is robust against geometric distortion attacks as well as signal-processing attacks.
其他識別: U0005-1301200915280100
Appears in Collections:資訊科學與工程學系所



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.