臺灣博碩士論文加值系統

本篇論文提出一個修補影片的系統，其主要的偵測對象是短暫性出現的雜訊。我們利用以區塊為基礎的移動估計，使用SAD（Sum of Absolute Difference）公式計算移動向量，進而偵測出雜訊。接著再將偵測到的雜訊過濾，最後再利用temporal及spatial的資訊雙重修補。Spatial的修補方法是利用多重解析度影像修補（multi- resolution image inpainting）。
本研究的結果，可以透過我們的偵測與過濾的演算法，成功地將毀損的區域偵測並修補；大部分的雜訊都可以成功的被偵測到，偵測率約為90%；而其修補後的結果也非常平滑、影片瀏覽順暢，視覺效果與原本影片非常相近，實作結果很好。

Video inpainting uses spatial-temporal information to repair defects such as spikes and lines on aged films. We propose a series of new algorithms based on adjustable thresholds to repair different varieties of aged films. The main contribution is an automatic spike and dirt detection mechanism. We prove that if appropriate threshold is once decided by the author, almost all damages in an aged video clip can be detected. In addition, the repairing procedure first estimates temporal information and obtain replacement blocks among several frames. Spatial information is then used to repair damages that can not be fixed by temporal information due to fast motion. The results are visually pleasant with most defects removed.

第一章 緒論 1
1.1 研究動機與目的 1
1.2 相關背景 4
1.3 論文架構 12
第二章 相關研究 13
第三章 相關技術 20
3.1 移動估計 20
3.1.1 搜尋的範圍 23
3.1.2 計算最佳區塊的公式 23
3.1.3 搜尋的方法 25
3.2 影像修補 33
第四章 演算法 42
4.1 系統架構 43
4.2 程式流程 45
4.3 程式演算法 48
4.3.1 偵測演算法 51
4.3.2 過濾演算法 56
4.3.3 修補演算法 60
第五章 實驗結果與討論 65
5.1 實作分析 65
5.2 實驗結果 71
第六章 結論與未來方向 82
參考文獻 84
英文論文 A1

[1] Alberto Machì and Fabio Collura, Accurate spatio-temporal restoration of compact single frame defects in aged motion pictures, Proceedings of the 12th International Conference on Image Analysis and Processing, pp.454-459, 17-19 September 2003.
[2] Anat Levin, Assaf Zomet and Yair Weiss, Learning how to inpaint from global image statistics, Proceedings of the Ninth IEEE International Conference on Computer Vision, pp.305-312, 13-16 October 2003.
[3] Alberto Machí and Mario Tripiciano, Video shot detection and characterisation in semi-automatic digital video restoration, Proceedings of the 15th International Conference on Pattern Recognition, Vol.1, pp.855-859, 3-7 September 2000.
[4] Bertalmio, M., Vese, L., Sapiro, G., Osher, S., Simultaneous structure and texture image inpainting, Proceedings of the 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol.2, pp.II-707-712, 18-20 June 2003.
[5] Chih-Ying Liao, Fast correlation block matching algorithm based on partial distortion for video compression, 義守大學資訊工程學系碩士班碩士論文, pp.10-49, June 2003.
[6] K. Deergha Rao, M. N. S. Swamy and E. L. Plotkin, Adaptive filtering approaches for colour image and video restoration, IEEE Proc-Vis. Image Signal Process, Vol.150, No.3, pp.168-177, June 2003.
[7] Kedar A. Patwardhan and Guillermo Sapiro, Projection based image and video inpainting using wavelets, Proceedings of the 2003 International Conference on Image Processing, Vol.1, pp.857-860, 14-17 September 2003.
[8] Kedar A. Patwardhan, Guillermo Sapiro and Marcelo Bertalmio, Video inpainting of occulding and oculded objects, www.tc.umn.edu /~patw0007/icip2005/index.html.
[9] Kokaram, A.C., On missing data treatment for degraded video and film archives: a survey and a new Bayesian approach, IEEE Transactions on Image Processing, Vol.13, Issue.3, pp. 397-415, March 2004.
[10] L. Joyeux, O. Buisson, B. Besserer, S. Boukir, Detection and removal of line scratches in motion picture films, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol.1, pp.548-553, 23-25 June 1999.
[11] Laurent Joyeux, Samia Boukir and Bernard Besserer, Film line scratch removal using Kalman filtering and Bayesian restoration, Fifth IEEE Workshop on Applications of Computer Vision, pp.8-13, 4-6 December 2000.
[12] Lucia Maddalena, Efficient methods for scratch removal in image sequences, Proceedings of the 11th International Conference on Image Analysis and Processing, pp.547-552, 26-28 September 2001.
[13] Michele Ceccarelli and Alfredo Petrosino, High performance motion analysis for video restoration, Processing of the 14th International Conference on Digital Signal, DSP 2002, Vol.2, pp.689-692, 1-3 July 2002.
[14] Michele Ceccarelli, Giuliano Laccetti and Alfredo Petrosino, High performance missing data detection and interpolation for video compression and restoration applications, Proceedings of the International Parallel and Distributed Processing Symposium, pp.1-5, 22-26 April 2003.
[15] O. Buisson, B. Besserer, S. Boukir, F. Helt, Deterioration detection for digital film restoration, Proceedings of the 1997 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp.78-84, 17-19 June 1997.
[16] Shih, T.K., Liang-Chen Lu, Ying-Hong Wang, Rong-Chi Chang, Multi-resolution image inpainting, Proceedings of the 2003 International Conference on Multimedia and Expo, 2003. ICME ''03., Vol. 1, pp.I-485-488, 6-9 July 2003.
[17] Sławomir Skoneczny, Defects removing in old movies, Proceedings of the 2nd, International Symposium on Image and Signal Processing and Analysis, ISPA 2001, pp.38-42, 19-21 June 2001.
[18] Walter J. Gillner, Motion based vehicle detection on motorways, Proceedings of the Intelligent Vehicles ''95 Symposium., pp.483-487, 25-26 September 1995.
[19] Wei-Qui Yan, Mohan S. Kankanhalli, Erasing Video logos based on image inpainting, Proceedings of the 2002 IEEE International Conference on Multimedia and Expo, ICME ''02. Vol.2, pp.521-524, 26-29 August 2002.
[20] Vittoria Bruni and Domenico Vitulano, A generalized model for scratch detection, IEEE Transactions on image processing, Vol.13, No.1, January 2004.
[21] Yamauchi, H., Haber, J., Seidel, H.-P., Image restoration using multiresolution texture synthesis and image inpainting, Proceedings of the Computer Graphics International, pp.120-125, 9-11 July 2003.
[22] Yi Zhang and Tat-Seng Chua, Detection of text captions in compressed domain video, Proceedings of the 2000 ACM workshops on Multimedia, pp.201-204, November 2000.