過去幾年來，有相當多的研究學者提出各種不同關於移除物件的影像修復法。其中最著名的有兩類：一個是基於偏微分方程式之影像擴散修復法，這個方法是將未毀損的影像資訊利用擴散的方式傳遞到毀損的區域，所以當毀損區域過大時，修復後的影像結果會產生模糊。另一個是紋理取樣修復法，這個方法是利用紋理比對的方式，將影像資訊從未毀損的區域複製到毀損的區域內，而且它可以修復較大面積的毀損區域。但是此方法針對非線性的影像結構無法正確的修復，並且也容易有紋理取樣失誤的問題。因此本篇論文主要針對紋理取樣修復法的缺點進行改良，我們同樣採用紋理取樣修復法的概念，並且加入紋理分割和結構重建。透過紋理分割可以使得我們在紋理取樣的時候能夠節省搜尋時間，增加修復後影像紋理的準確度。另外在結構重建時，我們會對已知區域的影像結構做分析，並且利用非線性的曲線來重建毀損區域內的影像結構。在我們的實驗當中，可以明顯地看出本篇論文所提出的演算法在影像結構和紋理的修復上，相較於傳統的紋理取樣修復法要來說更為的合理和適宜。

In past years, several researchers proposed various image inpainting algorithms for removing objects. There are two popular inpainting algorithms among previous works. The first one is the PDE-based image inpainting, which propagates image in-formation into target regions via diffusion. The main drawback of PDE-based image inpainting is the result image with some blurring effect in target regions when the area is large. The second one is the exemplar-based image inpainting, which copies image information to target regions by texture comparison, and can restore large occluding objects, but exemplar-based image inpainting cannot correctly reconstruct non-linear image structures, and furthermore, it causes texture sampling error frequently. The main contribution of this thesis is to improve the drawbacks of exemplar-based image inpainting. We introduce the same concept of exemplar-based image inpainting into our algorithm, then preprocess target image with texture segmentation and structure reconstruction. By our proposed algorithm, the time consumption of searching texture is reduced and the accuracy of texture sampling by texture segmentation increases. In structure reconstruction, we analyze all structures in the image except the target re-gions, and reconstruct image structures with non-linear curves in the target regions. Our experiments show that the reconstructed structures and textures of result image are favorably compared to those of conventional exemplar-based image inpainting techniques.

[1] M. Bertalmio, G. Sapiro, V. Caselles, and C. Ballester, “Image inpainting,” in Proc. ACM Conf. Comp. Graphics (SIGGRAPH), New Orleans, LA, July 2000, pp. 417–424.
[2] T. F. Chen and J. Shen, “Non-texture inpainting by curvature–driven diffusions,” J.Vis. Comm. Image Rep., vol. 4, mo. 12, pp.436-449, 2001.
[3] C. A. Z. Barcelos and M. A. Batista, “Image restoration using digital inpainting and noise removal,” Image and Vision Computing, vol. 25, no. 1, pp. 61-69 Jan. 2007.
[4] R. Bornard, E. Lecan, L. Laborelli, and J.-H. Chenot,“Missing data correction in still images and image sequences,” in ACM Multimedia, France, Dec. 2002.
[5] A. Criminisi, P. Perez, and K. Toyama, “Region filling and object removal by examplar-based image inpainting,” IEEE Trans. Image Process., vol. 13, no. 9, pp. 1200–1212, Sep. 2004.
[6] J. Wu and Q. Ruan, “Object Removal by Cross Isophotes Exemplar-based In-painting,” International Conference on Pattern Recognition, vol. 3, pp. 810-813, 2006.
[7] J. Shen, X. Jin, C. Zhou, and C. C.L. Wang, “Gradient based image completion by solving the Poisson equation,” Computers & Graphics, vol. 31, no. 1, pp. 119-126, Jan 2007.
[8] M. Bertalmio, L. Vese, G. Sapiro, and S. Osher, “Simultaneous structure and texture image inpainting,” IEEE Trans. Image Process., vol. 12, no. 8, pp. 882-889, Aug. 2003.
[9] X. Shao, Z. Liu, and H. Li, “An image inpainting approach based on the Poisson equation,” Second International Conference on Document Image Analysis for Libraries, DIAL 2006 2006, art. no. 1612979, pp. 368-372.
[10] P. Perona and J. Malik, “Scale space and edge detection using anisotropic diffu-sion,” IEEE Trans. Patten Anal. Machine Intell., vol 12, no. 7 pp. 629-639, July 1990.
[11] M. J. Black, G. Sapiro, D. H. Marimont, and D. Heeger, “Robust Anisotropic dif-fusion,” IEEE Trans. Image Process., vol. 7, no. 3, pp. 421-432, Mar. 1998.
[12] Y. Deng and B. S. Manjunath, “Unsupervised segmentation of color-texture re-gions in images and video,” IEEE Trans. Pattern Analysis and Machine Intelli-gence, vol. 23, no. 8, pp. 800-810, Aug. 2001.
[13] I. S. Hsieh and K. C. Fan, “An adaptive clustering algorithm for color quantiza-tion,” Pattern Recognition Letters, vol. 21, pp. 337-346, Apr. 2000.
[14] Y. H. Kuan, C. M. Kuo, and N. C. Yang, “Color-Based Image Salient Region Segmentation Using Novel Region Merging Strategy,” IEEE Trans. Multimedia, vol. 10, no. 5, pp. 832-845, Aug. 2008.
[15] A. Rares, M. J. T. Reinders, and J. Biemond, “ Edge-based image inpainting,” IEEE Trans. Image Process., vol. 14, no. 10, pp. 1454-1468, Oct. 2005.
[16] E. Angel, Interactive Computer Graphics: A Top-Down Approach Using OpenGL, 4th Edition, Addison Wesley, 2006.