本篇論文提供一個新的影像補全之技術，可用於重建已受損的影像並且結果可以被人眼所接受。為了使結果可以欺騙過人的眼睛，本篇論文首先提出一個新的曲線重建之技術，此技術可以自動的重建影像中的結構部分使受損區域的邊緣與背景的邊緣可以平滑的連接。本論文與傳統需要手動繪製物體邊緣結構的技術的不同點在於本論文所提供的技術可以根據受損區域周圍的物體邊緣來推測出受損區域中最合理的物體結構。當執行完影像的結構補全後，受損區域中仍有紋理影像尚未被完成，此時便用紋理合成的技術將剩下的物體紋理影像補全。這樣先執行結構補全再執行紋理補全的方法可優先考慮高頻的影像，因為人眼對高頻影像較為敏感，所以先處理高頻之影像可以提高人眼的接受度。從實驗結果可證明本論文所提供的方法擁有影像重建以及補全的能力。

In this thesis, a novel image completing technique is proposed for repairing a damaged image to a complete one. To well cheat human eyes, a novel curve repairing technique is first proposed to automatically recover image structures for smoothing the boundaries between the damaged regions and the background. Different from traditional image repairing techniques which need manual efforts for recovering image structures, the proposed technique can infer the best object shape by collecting various cues from edge points around the damaged region. When the structure propagation process is finished, a texture synthesis technique is designed to propagate objects’ texture features into the damage area. Thus, the high frequency components can be well estimated and embedded into the damaged areas. Experiments were conducted on various images and the results reveal the superiority of our proposed method in image repainting and completing.

[1] M. Ashikhmin, "Synthesizing Natural Textures" ACM Symposium on Interactive 3D Graphics, P. 217-226, March 2001.
[2] A. A.Efros and W. T. Freeman, “Image Quilting of Texture Synthesis and Transfer,” ACM SIGGRAPH, P.341-346, August 2001.
[3] R. Bellman, Dynamic Programming. Princeton University Press, Princeton, NJ, 1957.
[4] V. Kwatra, A. Arno Schödl, I. Essa, G. Turk and A. Bobick, “Gaphcut Textures: Image and Video Synthesis Using Graph Cuts,” ACM Transactions on Graphics, ACM SIGGRAPH, 2003.
[5] L.-Y. Wei and M. Levoy, “Fast Texture Synthesis using tree-structured vector quantization,” ACM SIGGRAPH 2000, P. 479-488, 2000.
[6] L. Liang, C. Liu, Y.-Q. Xu, B. Guo and H.-Y. Shum, “Real-time Texture Synthesis by patch-based Sampling,” ACM Transactions on Graphics, Vol. 20, No. 3, P.191-150, 2001.
[7] Y. Xu, B. Guo and H.-Y. Shum, “Chaos mosaic: Fast and memory efficient texture synthesis,” Tech. Rep. MSR-TR-2000-32, Microsoft Research, 2000.
[8] A. Criminisi, P. Pérez and K. Toyama, “Object Removal by Exemplar-based Inpainting,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition,Vol. 2, P.721-728, 2003.
[9] I. Drori, D. Cohen-Or and H. Yeshurun, “Fragment-based Image Completion,” ACM Transactions on Graphics, Vol. 22, P.303-312, 2003.
[10] J. Sun, L. Yuan, J. Jia and H. Shum, “Image Completion with Structure Propagation,” ACM SIGGRAPH 2005, P.861-868, 2005.
[11] A. Sharf , M. Alexa and D. Cohen-Or, “Context-based surface completion,” ACM SIGGRAPH, P.878-887, 2004.
[12] P. Pérez, M. Gangnet and A. Blake, “Poisson Image Editing,” ACM SIGGRAPH, P.313-318, 2003.
[13] A. Schödl, R. Szeliski, D. H. Salesin and I. Essa, “Video Texture,” Proceedings of SIGGRAPH, P.489-498, 2000.
[14] M. Bertalmio, A. L. Bertozzi and G. Sapiro, “Navier-stokes, Fluid dynamics and image and video inpainting,” Conf. Comp. Vision Pattern Rec., 2001.
[15] W. T. Freeman, E. C. Pasztor and O. T. Carmichael, “Learning low-level vision,” Int. J. Computer Vision, 40(1):25-47, 2000.
[16] A. Hertzmann, C. E. Jacobs, N. Oliver, B. Curless and D. H. Salesin, “Image Analogies,” SIGGRAPH, 2001.
[17] Y. Boykov, O. Veksler and R. Zabih, “Fast Approximate Energy Minimization via Graph Cuts,” International Conference on Computer Vision, P.377-384, 1999.
[18] J. Canny, “A Computational Approach to Edge Detection,” IEEE Transactions on Pattern Analysis and Machine intelligence, Vol. PAMI-8, No. 6, November 1986.
[19] W. H. Press, S. A. Teukolsky, W. T. Vetterling and B. P. Flannery, “Numerical Recipes: The Art of Scientific Computing,” Cambridge University Press, 3 edition.
[20]PlanetMath.org(http://planetmath.org/?op=getobj&from=objects&id=1195)