(3.237.97.64) 您好!臺灣時間:2021/03/05 02:30
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:彭智郁
研究生(外文):Chih-Yu Peng
論文名稱:具多重解析度之混合影像修補演算法
論文名稱(外文):A Multi-resolution Approach for Hybrid Image Inpainting
指導教授:吳俊霖吳俊霖引用關係
口試委員:陳志榮王周珍
口試日期:2011-07-06
學位類別:碩士
校院名稱:國立中興大學
系所名稱:資訊科學與工程學系所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2011
畢業學年度:99
語文別:中文
論文頁數:58
中文關鍵詞:影像修補多重解析度影像材質合成基於範例修補法邊緣結構重建貝茲曲線
外文關鍵詞:image inpaintingMulti-resolution imageTexture synthesisExemplar-based methodEdge structure reconstructionBezier curve
相關次數:
  • 被引用被引用:0
  • 點閱點閱:128
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
影像修補是一種將影像中受損或遺失的區域修補回去的技術,其主要是藉由影像中已知的資訊來修復被破壞的區域,修復後的影像必須是自然、人眼看起來像是未經受損的,然而影像結構的修復仍是目前的一大挑戰,目前的研究針對修復平滑的曲線結構有不錯的效果,但當修復的是包含了材質特性的結構時卻不容易修復。為了能夠同時修復影像的結構和材質,本篇論文參考了A.Rares等人提出的影像邊緣的重建、Wu和Chou所提的貝茲曲線影像修補、Criminisi等人所提出的範例影像修補方法,提出了具多重解析度之混合影像修補演算法。在低解析度影像時利用待修補區域周圍的邊緣資訊進行邊緣的配對以找出最佳的結構,然後利用貝茲曲線來描繪出邊緣的結構,再將描繪出的邊緣結構所在位置對應到高解析度影像,然後以一個區塊為單位找最配對的邊緣區塊來進行修補,結構修補完後剩餘的部分就採用範例影像的修補方式,一樣是以一個區塊為單位,從影像中已知的區域當中找到最佳配對的區塊填補回去,可以有效的將受損區域修補完成,且大致上都能維持影像的結構與材質特性。為了避免不必要的瑕疵出現及確保影像的完整性,所以最後我們加入Hsu等人提出的瑕疵偵測法,能夠再次確認修補完的影像是否有不自然的地方,針對有瑕疵的部分再次進行範例影像修補,可以達到較好的修補效果。

The filling-in of missing region in an image, which is called image inpainting, is an important topic in the field of computer graphics and image processing. The basic idea behind the technique is to automatically fill in lost or broken parts of image by using the information from the already known region. The challenge of the current inpainting algorithms is how to restore both of texture and structure characteristics information in an image. The current inpainting algorithms perform well in restoring the area with smooth structures, however, they can not restore the edges with texture. In this study, a new image inpainting method based on multi-resolution approach is presented, which combines exemplar-based inpainting technique, edge-based image restoration algorithm and Bezier-curves based image inpainting. The idea of our proposed method uses a low-resolution image to find the skeleton image structure in the missing areas, the edges with texture then become smooth after down-sampling. The inpainting method is divided into three phases, the first step is to finding the skeletons in the missing area from the low-resolution image, and then reconstruct the structure in the high-resolution image. The second step is to fill in the remainder region and the final step is to detect the artifact region and re-inpainting the area with artifact. After filling the missing region in the first pass, an artifact detection algorithm is used to find the artifact blocks in which the inpainting result is not satisfactory. We then adopt patch-based inpainiting method for preserving the texture information. Experimental results on both of artificial and real images demonstrate the effectiveness and robustness of the proposed multi-resolution inpainting method.

誌 謝.....................................................i
中文摘要...................................................ii
英文摘要..................................................iii
目錄......................................................iv
圖目錄......................................................v
第一章 諸論.................................................1
1.1 研究動機與背景...........................................1
1.2 論文架構................................................4
第二章 文獻回顧..............................................5
2.1. 基於偏微分方程的影像修補演算法.............................5
2.2. 材質合成...............................................8
2.3. 結合偏微分方程和材質合成之優點的影像修補演算法...............11
2.4. 基於範例影像修補演算法...................................17
2.5. 基於邊緣影像修補演算法...................................20
2.6. 基於貝茲曲線的影像修補演算法..............................28
2.7. 瑕疵偵測演算法.........................................31
第三章 所提的具多重解析度之混合影像修補演算法.....................35
3.1. 建立多重解析度影像......................................36
3.2. 低解析度影像骨架結構重建.................................37
3.3. 高解析度影像骨架結構重建及修補............................42
3.4. 基於範例的修補.........................................43
3.5. 瑕疵偵測..............................................44
第四章 實驗結果與討論........................................45
4.1. 影像結構的重建及影像的修復...............................45
4.2. 瑕疵偵測..............................................53
第五章 結論與未來工作........................................56
參考文獻...................................................57


[1] M. Bertalmio, G. Sapiro, V. Caselles, and C. Ballester, “Image inpainting”, Proc. of the ACM SIGGRAPH 2000, New Orleans, pp.417-424, July 2000.
[2] T. F. Chan and J. Shen, “Mathematical Models for Local Deterministic Inpaintings”, Technical Report CAM 00-11, Image Processing Research Group, UCLA, Mar 2000.
[3] T. F. Chan and J. Shen, “Non-Texture Inpainting by Curvature Driven Diffusions (CDD)”, J. Vis. Comm. Image Rep., pp.436-449, 2001.
[4] M. M. Oliveira, B. Bowen, R. McKenna, and Y. S. Chang, “Fast Digital Image Inpainting,” in Processing of the International Conference on Visualization, Imaging and Image Processing(VIIP2001),pp.261-266, 2001.
[5] A. Telea, “An Image Inpainting Technique Based on the Fast Marching Method”, Journal of Graphics Tools, 9 (1), pp.25-36, 2004.
[6] D. J. Heeger and J. R. Bergen, “Pyramid-based texture analysis/synthesis,” in Proc. ACM Conf. Computer Graphics, Los Angeles, CA, vol. 29, pp. 229–233,1995.
[7] J. Portilla and E. P. Simoncelli, “A parametric texture model based on joint statistics of complex wavelet coefficients,” International Journal of Computer Vision, vol. 40, no. 1, pp. 49–71, Oct. 2000.
[8] A. Efros and T. Leung, “Texture synthesis by non-parametric sampling,” in Proc. Int. Conf. Computer Vision, Kerkyra, Greece, pp. 1033–1038, Sep.1999.
[9] L. Y. Wei and M. Levoy, “Fast texture synthesis using tree-structured vector quantization,” in Proc. ACM Conf. Computer Graphics, pp. 479–488, Jul. 2000.
[10] M. Ashikhmin, “Synthesizing natural textures,” in Proc. ACM Symp. Interactive 3D Graphics, pp. 217–226, Mar. 2001.
[11] S. C. Pei, Y. C. Zeng, and C. H. Chang, “Virtual restoration of ancient Chinese paintings using color contrast enhancement and Lacuna texture synthesis,” IEEE Trans. Image Process., vol. 13, no. 3, pp. 416–429, Mar. 2004.
[12] A. Efros and W. T. Freeman, “Image quilting for texture synthesis and transfer,” in Proc. ACM Conf. Computer Graphics, pp. 341–346, Aug. 2001.
[13] L. Liang, C. Liu, Y. Q. Xu, B. Guo, and H. Y. Shum, “Real-time texture synthesis by patch-based sampling,” ACM Trans. Graph., vol. 20, pp. 127–150, July 2001.
[14] V. Kwatra, A. Schodl, I. Essa, G. Turk, and A. Bobick, “Graphcut textures: Image and video synthesis using graph cuts,” in Proc. SIGGRAPH, pp. 277–286, 2003.
[15] M. Bertalmio, L. Vese, G. Sapiro, and S. Osher, “Simultaneous structure and texture image inpainting,” IEEE Trans. Image Processing, vol. 12, no. 8, Aug. 2003.
[16] J. Sun, L. Yuan, J. Jia, and H.-Y. Shum, “Image Completion with Structure Propagation,” ACM Trans. on Graphics, pp.861-868, July 2005.
[17] Antonio Criminisi, Patrick Perez, and Kentaro Toyama, “Region filling and object removal by exemplar-based image inpainting,” IEEE transactions on image processing, vol. 13, no. 9, Sept. 2004
[18] A.Rares, M.J.T.Reinders, and J.Biemond, “Edge-based image restoration,” IEEE Trans. Image Processing, 14(10):1454-1468, 2005.
[19] I. Drori, D. Cohen-Or, and H. Yeshurun, “Fragment based image completion,” in ACM Trans. Graphics (SIGGRAPH), vol. 22, San Diego, CA, pp. 303–312, 2003.
[20] J. Jia and C.-K. Tang, “Image repairing: Robust image synthesis by adaptive nd tensor voting”, in Proc. Conf. Computer Vision and Pattern Recognition, Madison, June 2003.
[21] H. Yamauchi, J. Haber, and H. P. Seidel, “Image Restoration using Multiresolution Texture Synthesis and Image Inpainting”, Proc. Computer Graphics International (CGI), pp. 120-125, July 2003.
[22] H. Grossauer, “A Combined PDE and Texture Synthesis Approach to Inpainting,” European Conference on Computer Vision, LNCS 3022, pp. 214-224, 2004.
[23] BianRu Li, Yue Qi, and XuKun Shen , “An image inpainting method” , Computer Aided Design and Computer Graphics, 2005.
[24] Nikos Komodakis and Georgios Tziritas, “Image Completion Using Efficient Belief Propagation Via Priority Scheduling and Dynamic Pruning,” IEEE transactions on image processing, vol. 16, no. 11, November 2007.
[25] L. Dong, G.Yu, P. Ogunbona, W. Li, “An efficient iterative algorithm for image thresholding,” Pattern Recognition Letters, vol. 29, pp.1311-1316, 2008.
[26] J. L. Wu and I. Y. Chou, “An Effective Content-Aware Image Inpainting Method,” Accepted by Journal of Information Science and Engineering, December 2010.
[27] H. J. Hsu, J. F. Wang, and S. C. Liao, “A Hybrid Algorithm With Artifact Detection Mechanism for Region Filling After Object Removal From Digital Photograph,” IEEE transactions on image processing, vol. 16, no. 6, June 2007
[28] Test images are from : http://www.nipic.com, http://tooopen.com, http://www.cyps.hlc.edu.tw, http://pic.chaokers.cn, http://www.wallcoo.com/, http://www.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/segbench/

QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔