請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/32816
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 莊永裕(Yung-Yu Chuang) | |
dc.contributor.author | Chieh-Ju Tu | en |
dc.contributor.author | 涂介儒 | zh_TW |
dc.date.accessioned | 2021-06-13T04:16:16Z | - |
dc.date.available | 2006-08-01 | |
dc.date.copyright | 2006-08-01 | |
dc.date.issued | 2006 | |
dc.date.submitted | 2006-07-25 | |
dc.identifier.citation | [1] P. Schallauer, A. Pinz, and W. Haas, 'Automatic Restoration Algorithms for 35 mm Film,' Videre: Jounal of Computer Vision Research, 1993.
[2] A. C. Kokaram, 'Motion Picture Restoration,' PhD thesis, at Churchill Col-lege, 1993. [3] L. Joyeux, O.Buisson, B. Besserer, and S. Boukir, 'Detection and Removal of Line Scratches in Motion Picture Films,' Computer Vision and Pattern Rec-ognition, 1999. [4] A. C. Kokaram, R. D. Morris, W. J. Fitzgerald, and P. J. W. Rayner, 'Detec-tion of Missing Data in Image Sequence,' IEEE TRANSACTIONS ON IMAGE PROCESSING, 1995. [5] A. C. Kokaram, R. D. Morris, W. J. Fitzgerald, and P. J. W. Rayner, 'Interpo-lation of Missing Data in Image Sequences,' IEEE TRANSACTIONS ON IMAGE PROCESSING, 1995. [6] A. Rares, M. J. T. Reinders, and J. Biemond, 'Complex Event Classification in Cegraded Image Sequences,' ICIP, 2001. [7] A. Rares, M. J. T. Reinders, and J. Biemond, 'Recovery of Partially Degraded Colors in Old Films,' Eusipco, 2002. [8] A. Rares, M. J. T. Reinders, J.Biemond, and R. L. Lagendijk, 'A SPATIOTEMPORAL IMAGE SEQUENCE RESTORATION ALGORITHM,' ICIP2002, International Conference on Image Processing, 2002. [9] P. Viola and M. Jones, 'Robust Real-time Object Detection,' Workshop on Statistical and Computational Theories of Vision - Modeling, Learning, Com-puting, and Sampling, 2001. [10] Y. Freund and R. E. Schapire, 'A decision-theoretic generalization of on-line learning and an application to boosting,' Journal of Computer and System Sciences, 1996. [11] A. Criminisi, P. P'erez, and K. Toyama, 'Object Removal by Exemplar-based Inpainting,' Computer Vision and Pattern Recognition, 2003. [12] Y. Wexler, E. Shechtman, and M. Irani, 'Space-time video completion,' Computer Vision and Pattern Recognition, 2004. [13] Y. Matsushita, E. Ofek, X. Tang, and H.-Y. Shum., 'Full-frame Video Stabi-lization,' Computer Vision and Pattern Recognition, 2005. [14] T. Shiratori, Y. Matsushita, S. B. Kang, and X. Tang, 'Video Completion by Motion Field Transfer,' Computer Vision and Pattern Recognition, 2006. [15] J. Jia, T.-P. Wu, Y.-W. Tai, and C.-K. Tang, 'Video Repairing: Inference of foreground and background under severe occlusion,' Computer Vision and Pattern Recognition, 2004. [16] K. A. Patwardhan, G. Sapiro, and M. Bertalmio, 'Video Inpainting of Oc-cluding and Occluded Objects,' Int'l Conf. on Image Processing, 2005. [17] Y. Zhang, J. Xiao, and M. Shah., 'Motion layer based object removal in vid-eos,' IEEE Workshop on Applications of Computer Vision, 2005. [18] L. Zitnick, N. Jojic, and S. Kang., 'Consistent Segmentation for Optical flow Estimation,' Int'l Conf. on Image Processing, 2005. [19] J. Xiao, H. Cheng, H. Sawhney, and M. I. Cen Rao, 'Bilateral Filtering-Based Optical Flow Estimation with Occlusion Detection,' European Conference on Computer Vision, 2006. [20] J.-Y. Bouguet., 'Pyramidal Implementation of the Lucas Kanade Feature Tracker: Description of the algorithm.,' Intel Research Laboratory, 1999. [21] M. J. Black and P. Anandan, 'A Framework for The Robust Estimation of Op-tical Flow,' International Conf. on Computer Vision, 1993. [22] M. J. Black and P. Anandan, 'The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow Fields,' Computer Vision and Image Understanding., 1996. [23] R. Schapire, 'A Boosting Tutorial,' www.cs.princeton.edu/~schapire. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/32816 | - |
dc.description.abstract | 這篇論文將會介紹一個數位影片修復(video restoration)的系統,這個系統可以修復大部分老舊發霉的影片。而這個論文主要有兩個貢獻。第一個貢獻是利用機器學習(machine learning)的方法自動偵測老舊影片發霉的部份。這個機器學習方法的名字叫做AdaBoost,它主要的作用在於選擇有效的特徵(features)用來學習。第二個貢獻是提出一個新的影像補洞(video inpainting)演算法用來修補偵測出來的破洞。這個方法與傳統的方法有著很大的不同,它最基本的原理是利用光學流動(optical flow)技術來填補破洞,除此之外我們利用反覆(iteration)的計算來加強結果,並減少因為光學流動估計所產生的錯誤。在本論文中還提供三段老舊發霉影片的修復片段,以及一段影像補洞演算法的結果。 | zh_TW |
dc.description.abstract | This thesis describes a video restoration framework that can handle most moldy pat-tern in an aged film. There are two key contributions. The first is a learning algorithm, based on AdaBoost, which selects a small number of critical features and yields an efficient strong classifier to detect moldy pattern in an aged film. The second is a new video inpainting algorithm which repairs the detected holes. This video inpainting al-gorithm is much different with traditional ones. It is based on the temporal informa-tion from the optical flow. Furthermore, we refine our result by iteration in order to reduce the error, which is generated by inaccurate estimation of optical flow. Three examples of aged film restoration, and one example of video inpainting are presented in this thesis. | en |
dc.description.provenance | Made available in DSpace on 2021-06-13T04:16:16Z (GMT). No. of bitstreams: 1 ntu-95-R93944013-1.pdf: 8420645 bytes, checksum: 11ad413c503198453f687338d301b73f (MD5) Previous issue date: 2006 | en |
dc.description.tableofcontents | CHAPTER 1 INTRODUCTION 1
1.1 DEFECTS OVERVIEW 1 1.2 SYSTEM OVERVIEW 3 1.3 THESIS ORGANIZATION 4 CHAPTER 2 RELATED WORK 5 2.1 VIDEO RESTORATION 5 2.2 ADABOOST 6 2.3 VIDEO INPAINTING 7 2.4 OPTICAL FLOW 11 CHAPTER 3 MOLDY PATTERN DETECTION USING ADABOOST 13 3.1 ADABOOST INTRODUCTION[9, 10] 13 3.2 A SIMPLE EXAMPLE OF ADABOOST[23] 15 3.3 FEATURES 18 3.4 DETECTION RESULTS 23 CHAPTER 4 VIDEO INPAINTING USING OPTICAL FLOW 27 4.1 ALGORITHM PROTOTYPE 28 4.2 OUR VIDEO INPAINTING 33 4.3 RESULTS 36 CHAPTER 5 RESULTS 41 CHAPTER 6 CONCLUSIONS AND FUTURE WORK 49 6.1 CONCLUSIONS 49 6.2 FUTURE WORK 49 REFERENCE 51 | |
dc.language.iso | en | |
dc.title | 老舊發霉影片之數位修復 | zh_TW |
dc.title | Digital Restoration of Moldy Aged Films | en |
dc.type | Thesis | |
dc.date.schoolyear | 94-2 | |
dc.description.degree | 碩士 | |
dc.contributor.coadvisor | 陳炳宇(Bing-Yu Chen) | |
dc.contributor.oralexamcommittee | 歐陽明(Ming Ouhyoung) | |
dc.subject.keyword | 老舊,發霉,影片修復, | zh_TW |
dc.subject.keyword | video restoration,video inpainting,mold detection, | en |
dc.relation.page | 53 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2006-07-25 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 資訊網路與多媒體研究所 | zh_TW |
顯示於系所單位: | 資訊網路與多媒體研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-95-1.pdf 目前未授權公開取用 | 8.22 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。