研究生: |
羅健瑋 Chien-wei Lo |
---|---|
論文名稱: |
基於色彩差異演算法之影像修補技術 Am Image Inpainting Technique Based on the Color Difference Algorithm |
指導教授: |
黃昌群
Chang-chiun Huang |
口試委員: |
邱士軒
Shih-hsuan Chiu 郭中豐 Chung-feng Kuo |
學位類別: |
碩士 Master |
系所名稱: |
工程學院 - 材料科學與工程系 Department of Materials Science and Engineering |
論文出版年: | 2011 |
畢業學年度: | 99 |
語文別: | 中文 |
論文頁數: | 62 |
中文關鍵詞: | 色彩模型 、色彩差異 、影像修補 |
外文關鍵詞: | color model, color difference, image inpainting |
相關次數: | 點閱:210 下載:2 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
透過數位影像處理,我們可以任意的移除影像中的物件,並將移除物件後所留下的空白區域以周圍色彩像素填補,維持其影像之完整性。為了達到影像修補具自動填補目的,我們的研究將架構在基於範例之影像修補演算法下,然而,此演算法是以搜索整張影像,找尋相似度最高之有效影像區塊來填補空白區塊,容易造成運算時間過長;另外,在處理雜訊過多之影像時,容易造成修補之誤判。所以我們對此類演算法做延伸與改進。我們利用坎尼邊緣運算子計算邊緣梯度大小與方向,確保優先權計算函數能夠找出維持結構的影像修補順序。而後我們縮小影像可靠像素的搜尋範圍,使影像修補過程能改善耗時的缺點,接著將原始RGB色彩模型轉至CIELAB色彩模型,透過色彩差異的計算,以求達到更佳的影像修補結果。經由我們改善的修補演算法處理後的影像,影像品質(PSNR)皆高於30dB,而與原始演算法相較之下,系統修補時間更大幅縮短,結果證明了我們所提出的方法,不僅有效率,且能獲得令人滿意的修補品質。
We can remove objects from digital images and replace them with visually plausible backgrounds via digital image processing. For the purpose of patching up automatically to fill in damaged areas in the image, we choose the region filling and object removal by exemplar- based image inpainting as our main framework. This algorithm searches the entire image to find the highest similarity and effective block to fill the gap. So it is likely to cause long operation time. Besides, if damaged areas are covered by the image foreground, it may cause some error for structure extension. Therefore, this thesis does some extension and improvement for this algorithm. Firstly, we use the Canny edge detector to calculate edge gradient and direction. And then, the priority function can use them to find the correct patch order to maintain the image structure. Secondly, we reduce the searching reliable pixels area to improve the drawback of time-consuming. Finally, we convert RGB color model to CIELAB color model and use color difference to achieve better results of image inpainting. For all images via our image inpainting algorithm, their image quality values (PSNR) are higher than 30dB and system operation times are faster than the original algorithm. As a result, our image inpainting algorithm is not only time-saving but also reasonable for digital image inpainting.
[1] A. A. Efros and T. Leung, “Texture Synthesis by Non-Parametric Sampling ,” Int. Conf. on Computer Vision, Vol. 2, pp.1022-1038, 1999
[2]A. A. Efros and W. T. Freeman, “Image Quilting for Texture Synthesis and Transfer,” ACM SIGGRAPH Conf. on Computer Graphics, pp. 341-346, 2001.
[3]T. F. Chan and J. Shen. “Mathematical Models for Local Deterministric Inpainting,” SIAM J. Appl. Math, Vol. 62, no. 4, pp.1019-1043, 2001.
[4]T. F. Chan and J. Shen, “Nontexture Inpainting by Curvature-Driven Diffusions,” Journal of Visual Communication and Image Representation, Vol. 12, no. 4, pp. 436-449, 2001.
[5]R. H. Chan, Y. W. Wen and A. M. Yip, “A Fast Optimization Transfer Algorithm for Image Inpainting in Wavelet Domains,” IEEE Trans. on Image Processing, Vol. 18, no. 7, pp. 1467-1476, 2009.
[6]M. Bertalmio, G. Sapiro, V. Caselles and C. Ballester, “Image Inpainting,” ACM SIGGRAPH Conf. on Computer Graphics, pp. 417-424, 2000.
[7] M. Bertalmio, L. Vese, G. Sapiro and S. Osher, “Simultaneous Structure and Texture Image Inpainting,” IEEE Trans. on Image Processing, Vol. 12, no. 8, pp. 882-889, 2003.
[8] M. M. Oliveira, B. Bowen, R. McKenna and Y. S. Chang, “Fast Digital Image Inpainting,” Int. Conf. on Visualization, Imaging and Image Processing, pp. 261-266, 2001.
[9]A. Telea, “An Image Inpainting Technique Based on the Fast Marching Method,” Journal of Graphics Tools, Vol. 9, no. 1, pp. 25-36, 2004.
[10]H. Yamauchi, J. Haber and H. P. Seidel, "Image Restoration Using Multiresolution Texture Synthesis and Image Inpainting," IEEE Trans. on Computer Graphics International, pp. 108-113, 2003.
[11]J. Sun, L. Yuan, J. Jia and H. Y. Shum, “Image Completion with Structure Propagation,” ACM SIGGRAPH Trans. on Computer Graphics, Vol. 24, pp. 861-868, 2005.
[12]A. Rares, Marcel J. T. Reinders and J. Biemond, “Edge-Based Image Restoration,” IEEE Trans. on Image Processing, Vol. 14, no. 10, pp. 1454-1468, 2005.
[13]M. Elad, J. L. Starck, P. Querre and D. L. Donoho, “Simultaneous Cartoon and Texture Image Inpainting using Morphological Component Analysis (MCA)” Journal on Applied and Computer Harmon. Anal. 19, pp. 340-358, 2005.
[14]Z. Tauber, Z. N. Li and M. S. Drew, “Disocclusion by Inpainting for Image-Based Rendering,” IEEE Trans. on Systems, Man, and Cybernetics-Part C: Applications and Reviews, Vol. 37, no. 4, pp. 527-539, 2007.
[15]P. Elango and K. Murugesan, “Digital Image Inpainting Using Cellular Neural Network,” Journal of Open Problems in Computer Science and Mathematics, Vol. 2, no. 3, pp. 439-450, 2009.
[16]M. Ma, O. C. Au, S. H. Gary Chan and M. T. Sun, “Edge-Directed Error Concealment,” IEEE Trans. on Circuits and Systems for Video Technology, Vol. 20, no. 3, pp. 382-395, 2010.
[17]G. Peyre, “Texture Synthesis with Grouplets,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 32, no. 4, pp. 733-746, 2010.
[18]A. Criminisi, P. Perez and K. Toyama, “Region Filling and Object Removal by Exemplar-Based Image Inpainting,” IEEE Trans. on Image Processing, Vol. 13, no. 9, pp. 1200-1212, 2004.
[19]J. F. Canny, ”A Computational Approach to Edge Detection,” IEEE Trans. Pattern Anal. Mach. Intell., Vol. 8, no. 6, pp. 679-698, 1986.
[20] N. Otsu, “A Threshold Selection Method from Gray-Level Histogram,” IEEE Trans. on System, Man, and Cybernetics, Vol. 9, no. 1, pp. 62-66, 1979.
[21]鐘國亮編著,影像處理與電腦視覺第四版,東華書局,2008。
[22]蔡孟凱編著,C++Builder6完全攻略,上奇科技股份有限公司,2003。
[23]余明興編著,Borland C++ Builder程式設計經典,文魁資訊股份有限公司,2002。
[24]胡國瑞編著,顯示色彩工程學,全華圖書股份有限公司,2009。
[25]繆紹綱編譯,數位影像處理,台灣培生教育出版股份有限公司,2009。
[26]黃文吉編著,C++ Builder 與影像處理,儒林圖書有限公司,2005。