數位浮水印是一項能夠提供數位媒體保護與驗證的重要技術。藉由以往在數位浮水印、支持向量機器(SVMs)與可容忍位置圖(TPM)所進行的研究與相關經驗，在本論文中將對於特徵的選擇與TPM的產生方式提供一整體研究。
在本論文中提出一系列的靜態影像浮水印技術。經由實驗證實，本論文所提之靜態影像數位浮水印技術，不僅承襲此一系列浮水印技術的良好特質，更重要的是在各方面的效能提升。尤其在運算時間的降低與抵擋低通濾波尤其顯著。

本論文更將所提之靜態影像浮水印拓展至以場景為基礎之動態影片浮水印技術。藉由本論文所提之技術，在一段場景中經由每個畫面的浮水印萃取，最後終能取出完整之浮水印。在本論文中還探討了壓縮與共謀攻擊，實驗結果顯示，本論文所提以SVMs為基礎之浮水印技術是有效與具體可行。

Digital watermarking is an important technique for protection and identification of the content of digital multimedia. From our previous work on digital watermarking technique based on support vector machines (SVMs) and tolerable position map (TPM), a thorough study on feature selection and TPM generation is conducted. The improved system is endorsed by a complete set of experiments. It not only inherits the good characteristics from the original algorithm, but also shows significant improvements on time consumption as well as the robustness of low-pass filtering attacks. The proposed algorithm is also extended to a scene-based video watermarking technique. The excellent performance on NC values is achieved by averaging extracted watermarks from many frames of one scene into the final extracted watermark. The issue on collusion attacks is also detailed discussed. Our video watermarking technique is shown to be robust to video compression and collusion attacks. The proposed video watermarking technique has its novelty and practicability on SVM-applications.

Table of Contents

List of Figures	III
List of Tables	V
Chapter 1 Introduction	1
Chapter 2 Related Works	4
Chapter 3 Support Vector Machines	8
Chapter 4 The Watermarking Scheme for Still Images	12
4.1 Embedding Algorithm	13
4.1.1 Training information embedding	13
4.1.2 Owner’s signature embedding	17
4.2 Extraction Algorithm	18
4.2.1 X-SVM training for signature extraction	18
4.2.2 Signature extraction	19
4.3 Experimental Results	19
Chapter 5 Improved Scheme for Still Images	25
5.1 The overview of improved watermarking scheme	25
5.2 Features Analysis	27
5.3 Tolerable Position Map (TPM)	33
5.4 The Preprocess of the Watermark Embedding	40
5.5 Experimental Results for Improved Watermarking Scheme	40
5.5.1 Attack free results	41
5.5.2 Performance improvement of improved algorithms	44
5.5.3 Evaluation on various attacks	46
Chapter 6 The watermarking scheme for videos	49
6.1 The proposed scene-based video watermarking algorithm	49
6.2 Robustness to collusion attacks	53
6.3 Experiments for the video watermarking algorithm	57
Chapter 7 Conclusions	60
REFERENCES	61
 
List of Figures
Fig. 1: A linear separating hyperplane.	8
Fig. 2: The diagram of embedding system.	12
Fig. 3: A binary sequence of a watermark.	13
Fig. 4: (center element), its 4-neighbors, and the corresponding surroundings (shaded beige and yellow).	15
Fig. 5: Mask for 8-neighbors feature 1.	15
Fig. 6: Mask for cross-shaped feature 2.	16
Fig. 7: Mask for X-shaped feature feature 3.	16
Fig. 8: Owner’s signature embedding procedure.	18
Fig. 9: Host images and watermark image.	21
Fig. 10: Error rate for experimental images.	24
Fig. 11: PSNR for experimental images.	24
Fig. 12: The diagram of the watermark embedding system.	26
Fig. 13: 8-neighbors feature 1.	28
Fig. 14: Cross-shaped feature 2.	28
Fig. 15: Diamond-shaped feature 3.	29
Fig. 16: X-shaped feature 4.	29
Fig. 17: Performance on one feature used only.	30
Fig. 18: Performance on two features used.	30
Fig. 19: Performance on three features used.	31
Fig. 20: Performance on all four features used.	31
Fig. 21: Tolerable Position Maps.	35
Fig. 22: Performance on the TPM generated by JPEG.	36
Fig. 23: Performance on the TPM generated by blurring.	36
Fig. 24: Performance on the TPM generated by sharpening.	37
Fig. 25: Performance on the TPM generated by JPEG & blurring.	37
Fig. 26: Performance on the TPM generated by sharpening & blurring.	38
Fig. 27: Performance on the TPM generated by sharpening & JPEG	38
Fig. 28: Discarding and scribbling attacks and corresponding results	46
Fig. 29: The frames order for embedding procedure in one scene	54

 
List of Tables
Table 1: Common Kernel Functions.	11
Table 2: Lena.	22
Table 3: Peppers.	22
Table 4: Baboon.	22
Table 5: Airplane.	23
Table 6: House.	23
Table 7: Lena	42
Table 8: Peppers	43
Table 9: Baboon	43
Table 10: Airplane	43
Table 11: Sailboat	44
Table 12: comparison between the improved and original methods	45
Table 13: NC values for discarding and scribbling	47
Table 14: NC values for JPEG and JPEG2000 compression	47
Table 15: NC values for rotation attacks	48
Table 16: Snatch of testing videos	58
Table 17: Robustness for video application and video compression (NC values)	58
Table 18: NC values of the video watermarking scheme for no attack and compression attack	58
Table 19: Results of the proposed video watermarking scheme for WER attack	59

[1] P. Tsai, Y. C. Hu, C. C. Chang, “A color image watermarking scheme based on color quantization,” Signal Processing 84, pp. 95-106 (2004).
[2] M. Kutter, F. Jordan, F. Bossen, “Digital Signature of Color Images using Amplitude Modulation,” Electronics Imaging 7(2), pp.326–332 (1997).
[3] P. T. Yu, H. H. Tsai, D. W  Sun, “Digital Watermarking of Color Images Using Support Vector Machines,” 2003 National Computer Symposium (NCS'03) (2003).
[4] Y. G. Fu, R. M. Shen, L. P. Shen, X. S. Lei, “Reliable Information Hiding Based on Support Vector Machine,” INFORMATICA, Vol. 16, No. 3, pp.333–346 (2005). 
[5] T. Amornraksa , K. Janthawongwilai, “Enhanced images watermarking based on amplitude modulation,” Image and Vision Computing, pp.111–119 (2006).
[6] S. Joo, Y. Suh, J. Shin, H. Kikuchi, “A New Robust Watermark Embedding into Wavelet DC Components,” ETRI Journal, VOL. 24, NO. 5, pp.401-404 (2002).
[7] J. L. Liu, D. C. Lou , M. C. Chang, H. K. Tso, “A robust watermarking scheme using self-reference image,” Computer Standards & Interfaces, pp.356-367 (2006).
[8] R. Ni, Q. Ruan, H. D. Cheng, “Secure semi-blind watermarking based on iteration mapping and image features,” Pattern Recognition 38, pp. 357-368 (2005).
[9] C. S. Shieh, H. C. Huang, F. H. Wang, J. S. Pan, “Genetic watermarking based on transform-domain techniques,” Pattern Recognition, pp. 555-565 (2004).
[10] F. Y. Shih, Y. T. Wu, “Enhancement of image watermark retrieval based on genetic algorithms,” Journal of visual communication & image representation, pp. 115–133 (2005).
[11] S. H. Yen, C. J. Wang, “SVM Based Watermarking Technique,” Tamkang Journal of Science and Engineering, vol. 9, no. 2, pp.141-150, June (2006).
[12] S. H. Yen, C. J. Wang, and Y. T. Kao, “A Watermarking Scheme Based on SVM and Tolerable Position Map,” 2006 IEEE Conference on System, Man, and Cybernetics, pp.3170-3175 (2006).
[13] V. Vapnik, “The Nature of Statistical Learning Theory, Springer-Verlag,” New York, (1995).
[14] C. J. C. Burges, “A tutorial on support vector machines for pattern recognition,” Data Mining and Knowledge Discovery, Vol. 2, No. 2, pp. 121-167 (1998).
[15] J. C. Platt, “Fast training of support vector machines using sequential minimal optimization, Advances in Kernel Methods - Support Vector Learning,” B. Schölkopf, C. Burges, and A. Smola, eds., MIT Press, pp. 185-208 (1999).
[16] J. C. Platt, Adult and Web Site. http://www.research.microsoft.com/~jplatt
[17] S. S. Keerthi, S. K. Shevade, C. Bhattacharyya, K. R. K. Murthy, “Improvements to Platt’s SMO Algorithm for SVM Classifier Design,” Neural Computation, Vol. 13, pp. 637-649 (2001).
[18] C. W. Hsu, C. C. Chang, and C. J. Lin, “A Practical Guide to Support Vector Classification,”  http://www.csie.ntu.edu.tw/~cjlin/papers/
[19] G. Doërr , J. L. Dugelay, “A guide tour of video watermarking,” Signal Processing: Image Communication, pp. 263–282 (2003).
[20] G. Doërr and J. L. Dugelay, “Security Pitfalls of Frame-by-Frame Approaches to Video Watermarking,” IEEE Transactions on Signal Processing, Vol. 52, No. 10, pp. 2955 – 2964 (2004).
[21] S. Biswas, S. R. Das, E. M. Petriu, “An Adaptive Compressed MEPEG-2 Video Watermarking Scheme,” IEEE Transactions on Instrumentation and Measurement, vol.54, No.5, pp. 1853 – 1861 (2005).
[22] H. Shu, L. P. Chau, “A new scene change feature for video transcoding,” IEEE International Symposium on Circuits and Systems, pp. 4582 – 4585 (2005).
[23] Y. Zhai, M. Shah, “A general framework for temporal video scene segmentation,” Tenth IEEE International Conference on Computer Vision, pp. 1111 – 1116 (2005).
[24] M. Holliman, W.Macy, M. Yeung, “ Robust frame-dependent video watermarking,” Proc. SPIE, Security and Watermarking of Multimedia contents II, Vol. 3971, pp. 186-197 (2000).
[25] http://www.on2.com/downloads/vp7-personal