請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/64098完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 李明穗(Ming-Sui Lee) | |
| dc.contributor.author | Zong-Xian Li | en |
| dc.contributor.author | 李宗憲 | zh_TW |
| dc.date.accessioned | 2021-06-16T17:29:55Z | - |
| dc.date.available | 2015-08-20 | |
| dc.date.copyright | 2012-08-20 | |
| dc.date.issued | 2012 | |
| dc.date.submitted | 2012-08-15 | |
| dc.identifier.citation | [1] Open Source Computer Vision Library. Opencv.
[2] Photoshop Creative Suite 5. Adobe. [3] C. Barnes, E. Shechtman, A. Finkelstein, and D. B. Goldman. Patchmatch: a ran- domized correspondence algorithm for structural image editing. ACM Trans. Graph., 28(3):24:1-24:11, July 2009. [4] M. Bertalmio, G. Sapiro, V. Caselles, and C. Ballester. Image inpainting. In Proceed- ings of the 27th annual conference on Computer graphics and interactive techniques, SIGGRAPH '00, pages 417-424, New York, NY, USA, 2000. ACM Press/Addison- Wesley Publishing Co. [5] A. Criminisi, P. Perez, and K. Toyama. Object removal by exemplar-based inpaint- ing. In Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference on, volume 2, pages II-721 - II-728 vol.2, june 2003. [6] J. Hays and A. A. Efros. Scene completion using millions of photographs. In ACM SIGGRAPH 2007 papers, SIGGRAPH '07, New York, NY, USA, 2007. ACM. [7] U. A. Ignacio and C. R. Jung. Block-based image inpainting in the wavelet domain. The Visual Computer, 23:733-741, 2007. 10.1007/s00371-007-0139-2. [8] P. Perez, M. Gangnet, and A. Blake. Poisson image editing. In ACM SIGGRAPH 2003 Papers, SIGGRAPH '03, pages 313-318, New York, NY, USA, 2003. ACM. [9] R. G. V. Gioi, J. Jakubowicz, and J. -M. Morel. LSD: a Line Segment Detector. Image Processing On Line, 2012. [10] K. Subr, C. Soler, and F. Durand. Edge-preserving multiscale image decomposition based on local extrema. ACM Trans. Graph., 28(5):147:1-147:9, Dec. 2009. [11] J. Sun, L. Yuan, J. Jia, and H.-Y. Shum. Image completion with structure propaga- tion. In ACM SIGGRAPH 2005 Papers, SIGGRAPH '05, pages 861-868, New York, NY, USA, 2005. ACM. [12] A. Telea. An image inpainting technique based on the fast marching method. ACM Trans. Graph., 20:23-34, 2004. [13] H. Ting, S. Chen, J. Liu, and X. Tang. Image inpainting by global structure and tex- ture propagation. In Proceedings of the 15th international conference on Multimedia, MULTIMEDIA '07, pages 517-520, New York, NY, USA, 2007. ACM. [14] Y. Wexler, E. Shechtman, and M. Irani. Space-time video completion. In Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on, volume 1, pages I-120 - I-127 Vol.1, june-2 july 2004. [15] A. Wong and J. Orchard. A nonlocal-means approach to exemplar-based inpainting. In Image Processing, 2008. ICIP 2008. 15th IEEE International Conference on, pages 2600 -2603, oct. 2008. [16] J. Wu and Q. Ruan. Object removal by cross isophotes exemplar-based inpainting. In Pattern Recognition, 2006. ICPR 2006. 18th International Conference on, volume 3, pages 810 -813, 0-0 2006. [17] H. Zhou and J. Zheng. Adaptive patch size determination for patch-based image completion. In Image Processing (ICIP), 2010 17th IEEE International Conference on, pages 421 -424, sept. 2010. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/64098 | - |
| dc.description.abstract | 影像修補技術是近十年來被廣泛討論的技術之一,其為一種將受損影像或選
定刪去物後,利用影像中現有資訊來做修補的技術。目的在於經過修補的影像, 是可以自然、不易被人眼所看出異狀。但目前對於需修補的區域面積較大,又要 維持影像結構的一致性,是需要人為的介入,使用者必須先畫出影像結構的形 狀,否則很容易造成修補過後的影像,有結構不一致的問題產生。 在此論文中,提出了一種自動保留結構與材質一致性的影像修補技術,希望 不需人為介入就可以達成保留結構一致性的效果。在此,為找出影像的主體結 構,使用邊界保留(edge-preserving)的方法,把材質的部份做平滑的處理,接著利用邊界偵測(edge detection)的方法,抓出影像的主體結構線,最後藉由邊緣分析與串連(edge analysis and linking)推測出而被修補區域中所缺少的結構,接著以此結構為準則來做影像修補,修補結果要盡可能滿足推測出的結構,以此達成結構的延續與一致性。 在影像修補的過程中,演算法分別對影像的結構與材質部份採取不同的演算 法來做修補。其中針對影像中屬於結構的部份,採用全域修補的方式來進行修 補,而針對影像中屬於材質的部份則結合了材質生成和影像修補的演算法來進行 修補的動作。實驗的結果顯示,提出的方法能有效保留影像結構與材質的一致 性,並且也和其他影像修補方法以及Photoshop CS5做比較,來探討彼此修補過 後的差異。 | zh_TW |
| dc.description.abstract | Image Inpainting is a useful method for removing part of the objects in a image.Traditional inpainting techniques considered only the local informations, which may cause artifacts. In this thesis, a novel approach of inpainting for preserving structure consistence is proposed. It combines the advantages of both structure propagation and texture synthesis.
In the proposed algorithm, user intervenes only at the beginning for defining the damaged area, and the left completes automatically. The algorithm can be divided into three steps, pre-processing, structure propagation then texture synthesis. In pre-processing step, edge-preserving lter is used to smooth texture area, edge detection to nd structure edge and edge analysis and linking is used to guess structure edge in damaged area. In order to preserve the structure consistence, the proposed method use the guessed structure edge as guidance to perform structure propagation. In the repairing precessing, the proposed algorithm treat structure and texture with di erent algorithm. At structure propagation step, global optimization algorithm is used to perform image structure repair. In texture synthesis, inpainting and texture synthesis algorithm are integrated to inpaint the texture of image. Experiment result shows that the proposed algorithm preserve structure and texture consistence in effect. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-16T17:29:55Z (GMT). No. of bitstreams: 1 ntu-101-R99922091-1.pdf: 32607679 bytes, checksum: 0cebbf9c47d0609f5cbfdcbf99248850 (MD5) Previous issue date: 2012 | en |
| dc.description.tableofcontents | 誌謝 ii
Abstract iii 中文摘要 iv 圖目錄 vii 第一章緒論 1 第一節研究動機 1 第二節研究目的 2 第三節研究貢獻 2 第四節論文架構 4 第二章相關研究 5 第一節像素為主修補法 5 第二節區塊為主修補法 6 第三節整體最佳解修補法 7 第四節監督式學習修補法 9 第三章影像修補技術 10 第一節影像前置處理 11 壹、邊緣保留 12 貳、邊緣偵測 13 參、邊緣分析與串連 14 第二節影像結構修補 16 第三節影像材質生成 23 第四章實驗結果與討論 26 第一節實驗結果 26 第二節實驗結果討論 41 第五章結論與未來工作 45 第一節結論 45 第二節未來工作 46 參考文獻 47 | |
| dc.language.iso | zh-TW | |
| dc.subject | 影像修補 | zh_TW |
| dc.subject | 材質生成 | zh_TW |
| dc.subject | 全域最佳化 | zh_TW |
| dc.subject | 結構延伸 | zh_TW |
| dc.subject | Image Inpainting | en |
| dc.subject | Global Optimization | en |
| dc.subject | Texture Synthesis | en |
| dc.subject | Structure Propagation | en |
| dc.title | 保留結構與材質一致性的影像修補技術 | zh_TW |
| dc.title | Image Inpainting with Structure and Texture Consistency | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 100-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 莊永裕(Yung-Yu Chuang),廖偉凱(Wei-Kai Liao) | |
| dc.subject.keyword | 影像修補,全域最佳化,材質生成,結構延伸, | zh_TW |
| dc.subject.keyword | Image Inpainting,Global Optimization,Texture Synthesis,Structure Propagation, | en |
| dc.relation.page | 49 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2012-08-16 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
| 顯示於系所單位: | 資訊工程學系 | |
文件中的檔案:
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-101-1.pdf 未授權公開取用 | 31.84 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。
