請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/48419完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 莊永裕 | |
| dc.contributor.author | Chi-Yuan Chiang | en |
| dc.contributor.author | 江啟遠 | zh_TW |
| dc.date.accessioned | 2021-06-15T06:56:05Z | - |
| dc.date.available | 2016-08-23 | |
| dc.date.copyright | 2011-08-23 | |
| dc.date.issued | 2011 | |
| dc.date.submitted | 2011-08-19 | |
| dc.identifier.citation | Bibliography
[1] M. R. Banham and A. K. Katsaggelos. Spatially adaptive wavelet-based multiscale image restoration. IEEE Trans. Image Processing, 5:619–634, April 1996. [2] M. Bertalmio and G. Sapiro. Image inpainting. pages 417–424, 2000. [3] C. Charalambous, F. K. Ghaddar, and K. Kouris. Two iterative image restoration al- gorithms with applications to nuclear medicine. IEEE Trans Med Imaging, 11(1):2– 8, 1992. [4] K. Dale, M. K. Johnson, K. Sunkavalli,W. Matusik, and H. Pfister. Image restoration using online photo collections. In International Conference on Computer Vision, pages 2217–2224, 2009. [5] Y. HaCohen, E. Shechtman, D. B. Goldman, and D. Lischinski. Non-rigid dense correspondence with applications for image enhancement. ACM Transactions on Graphics (Proceedings of ACM SIGGRAPH 2011), 30(4):70:1–70:9, 2011. [6] M. K. Johnson, K. Dale, S. Avidan, H. Pfister, W. T. Freeman, and W. Matusik. Cg2real: Improving the realism of computer generated images using a large collec- tion of photographs. IEEE Transactions on Visualization and Computer Graphics, 2011. [7] S. Kagarlitsky, Y. Moses, and Y. Hel-Or. Piecewise-consistent color mappings of images acquired under various conditions. In ICCV, pages 2311–2318, 2009. [8] A. K. Katsaggelos. A general formulation of adaptive iterative image restoration algorithms. In Conf. Inf. Sciences and Systems, pages 42–47, Princeton, NJ, January 1986. [9] D. G. Lowe. Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision, 60:91–110, November 2004. [10] V. Oliveira and J. Nightingale. Maximum image restoration in nuclear medicine. Communications, Speech and Vision, IEE Proceedings I, 137(3):163 –169, june 1990. [11] P. Pérez, M. Gangnet, and A. Blake. Poisson image editing. In ACM SIGGRAPH 2003 Papers, SIGGRAPH ’03, pages 313–318, New York, NY, USA, 2003. ACM. [12] F. Pitié, A. C. Kokaram, and R. Dahyot. Automated colour grading using colour distribution transfer. Comput. Vis. Image Underst., 107:123–137, July 2007. [13] E. Reinhard, M. Ashikhmin, B. Gooch, and P. Shirley. Color transfer between images. IEEE Comput. Graph. Appl., 21:34–41, September 2001. [14] H. Soltanian-Zadeh, J.Windham, and A. Yagle. A multidimensional nonlinear edgepreserving filter for magnetic resonance image restoration. Image Processing, IEEE Transactions on, 4(2):147 –161, feb 1995. [15] C. Tomasi and R. Manduchi. Bilateral filtering for gray and color images. In Proceedings of the Sixth International Conference on Computer Vision, ICCV ’98, pages 839–, Washington, DC, USA, 1998. IEEE Computer Society. [16] E. R. C. (U.S.). Evaluation of motion-degraded images: proceedings. Number 1 in NASA SP. Scientific and Technical Information Division, National Aeronautics and Space Administration, 1969. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/48419 | - |
| dc.description.abstract | 影像的修復一直是電腦視覺領域中一個重要的課題，它包含了多種電腦視覺技術，如去雜訊、偵測、重新打光、顏色轉移、圖像修復...等。本論文的目的在於修復老舊立體照片的雜訊及亮度問題，利用從立體照片獲得的資訊結合現有的照片修復技術，去加強照片修復的效果。並藉由此項改進，提升使用者對老舊照片的立體視覺體驗。 | zh_TW |
| dc.description.abstract | Image restoration has been a major subject of computer vision. Repairing damaged photos requires several computer vision techniques such as denoising, detection, relighting, color-transfer, and inpainting.
In this thesis, we proposed an automatic system to repair noise and light inconsistency problems. Our approach combined modern image restoration techniques with additional information gathered from stereoscopic photographs to enhance the effect of image restoration and optimize stereoscopic experience of old stereoscopic photographs. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-15T06:56:05Z (GMT). No. of bitstreams: 1 ntu-100-R98944024-1.pdf: 17005555 bytes, checksum: 8c12d04c1b46197050d097382b10f03d (MD5) Previous issue date: 2011 | en |
| dc.description.tableofcontents | 致謝i
中文摘要ii Abstract iii 1 Introduction 1 1.1 Motivation and Objective . . . . . . . . . . . . . . . . . . . . . . . . . . 1 2 RelatedWork 3 3 Dust and Scratches Removal 4 3.1 Local Dust and Scratches Detection . . . . . . . . . . . . . . . . . . . . 5 3.2 Stereo Dust and Scratches Detection . . . . . . . . . . . . . . . . . . . . 5 3.3 Defect Removal . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 4 Patch-Based Histogram Matching 9 4.1 SIFT(Scale-Invariant Feature Transform) . . . . . . . . . . . . . . . . . 9 4.2 Local Histogram Matching . . . . . . . . . . . . . . . . . . . . . . . . . 10 4.3 Linear Blending . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 5 Results 13 6 Conclusion And FutureWork 22 Bibliography 23 | |
| dc.language.iso | en | |
| dc.subject | 圖像修復 | zh_TW |
| dc.subject | 照片修復 | zh_TW |
| dc.subject | 立體視覺匹配 | zh_TW |
| dc.subject | 重新打光 | zh_TW |
| dc.subject | 去雜訊 | zh_TW |
| dc.subject | stereo matching | en |
| dc.subject | Image restoration | en |
| dc.subject | inpainting | en |
| dc.subject | denoising | en |
| dc.subject | relighting | en |
| dc.title | 老舊立體影像之修復 | zh_TW |
| dc.title | Old Stereoscopic Image Restoration | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 99-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 陳文進,周承復 | |
| dc.subject.keyword | 照片修復,立體視覺匹配,重新打光,去雜訊,圖像修復, | zh_TW |
| dc.subject.keyword | Image restoration,stereo matching,relighting,denoising,inpainting, | en |
| dc.relation.page | 24 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2011-08-19 | |
| 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-100-1.pdf 未授權公開取用 | 16.61 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。