臺灣博碩士論文加值系統

在近幾年雖然有很多關於影像復原的方法被提出來，但是當遺失區域如果是包含線段部分時，這些方法並沒有辦法有效復原影像，主要原因是遺失區域內的線段不容易被預測出來。本論文提出使用線段預測法來預測出包含線段或邊緣的遺失部分，由於影像的灰階值通常是平滑的；因此，在影像復原上平滑灰階偵測法利用像素間的平滑度，使用現存圍繞在遺失區域附近之範圍，來填補該區域，所以本論文提出基於灰階平滑偵測法及線段預測法在影像復原上。在我們的實驗中，提出的方法是優於其他的影像復原法。

Although many image restoration methods had been proposed in recent years, the reconstructed image is not good when the missing region contains the lines in the image. The reason is that the direction of lines is not easy to be predicted in the missing region. In this study, the line prediction method is proposed to predict the lines and edges contained in the missing regions of images. Furthermore, the gray levels of pixels are usually smooth in the images. Thus, the smooth gray levels detection is proposed to restore the missing regions using the surrounded existed regions according to the smoothness of pixels in the image.Therefore, the new image restoration method based on smooth gray levels detection and line prediction method is proposed in this study.In our experiments, the proposed method outperforms the other methods.

目 錄
中文摘要 ……………………………………………………I
Abstract………………………………………………………II
目錄 …………………………………………………………III
表目錄 ………………………………………………………V
圖目錄………………………………………………………VI
第一章 緒論(Introduction)……………………………………1
1.1 影像復原概述……………………………………………1
1.2 研究動機 …………………………………………………1
1.3 文獻探討 …………………………………………………2
1.4 論文架構 …………………………………………………3
第二章 形態學(Morphological) ………………………………5
2.1形態學邊緣偵測(Morphological Edge Detection)…………5
2.2 膨脹(Dilation) ……………………………………………5
2.3 侵蝕(Erosion) ……………………………………………7
2.4 形態梯度(Morphological Gradient)………………………9
2.5 開閉運算(Opening and Closing)…………………………10
第三章 填補影像遺失的範圍(Filling In Missing Regions)…14
3.1 相連要素的抽取(Extraction of Connected Components)…14
3.2 灰階平滑偵測(Smooth Gray Levels Detection)…………16
3.3 線段預測法(Line Prediction Method)……………………19
3.4 修正邊緣與線段 ………………………………………22
第四章 實驗及結果(Experiments and Results)………………25
4.1 小面積的遺失區塊 ………………………………………32
4.2 大面積的遺失區塊的實驗 ………………………………36
第五章 結論(Conclusions)……………………………………44
參考文獻 ……………………………………………………45

[1] D. Zhang, and Z. Wang, “Image information restoration based on long-range correlation,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 12, No. 5, pp. 331-341, 2002.

[2] S. D. Rane, G. Sapiro, and M. Bertalmio, “Structure and texture filling-in of missing image blocks in wireless transmission and compression applications,” IEEE Transactions on Image Processing, Vol. 12, No. 3, pp. 296-303, 2003.

[3] M. Bertalmio, L. Vese, G. Sapio, and S. Osher, “Simultaneous structure and texture image inpainting,” IEEE Transactions on Image Processing, Vol. 12,Nno. 8, pp. 882-889, 2003.

[4] A. A. Efros, and T. K. Leung, “Texture synthesis by nonparametric sampling,” IEEE Int. Conf. Computer Vision, Sept., pp, 1033-1038, 1999.

[5] L. Y. Wei, and M. Levoy, “Fast texture synthesis using tree-structured vector quantization,” Proc. SIGGRAPH, July 2000.

[6] M. Bertalmio, G. Sapiro, V. Caselles, and C. Ballester, “Image inpainting,” Proc. SIGGRAPH, pp. 417-424, 2000.

[7] G. Email-Maile, The Restorer’s Handbook of Easel Painting, NewYork: Van Nostrand Reinhold, 1976.

[8] D. King, The Commissar Vanishes, NewYork: Holt, 1997.

[9] S. Walden, The Ravished Image, NewYork: St. Martin’s, 1985.

[10] C. Ballester, M. Bertalmio, V. Caselles, G. Sapiro, and J. Verdera, “Filling-in by joint interpolation of vector fields and gray levels,” IEEE Transactions on Image Processing, Vol. 10, No. 8, pp. 1200-1211, 2001.

[11] S. B. Yang and L. Y. Tseng, "Smooth side-match classified vector quantizer with variable block size," IEEE Transactions on Image Processing, Vol. 10, No. 5, pp. 677-685, 2001.

[12] D. S. Bloomberg, “Multiresolution morphological analysis of document images,” Proc. SPIE Visual Communication Image Processing, Vol. 1818, pp. 648-662, 1992.

[13] Y. M. Y. Hasan and L. J. Karam, “Morphological Text Extraction from Images,” IEEE Transactions on Image Processing, Vol. 9, No. 11, pp. 1978-1983. Nov. 2000.

[14] R. C. Gonzalez and R. E. Woods, “Digital Image Processing,” Tom Robbins, New Jersey, pp. 550-557, 2002.

[15] H. M. Lin and A. N. Willson, “Median filters with adaptive length,”IEEE Transactions Circuits System, vol. 35, pp. 675–690, June 1988.

[16] R. C. Hardie and K. E. Barner, “Rank conditioned rank selection filters for signal restoration,” IEEE Transactions Image Processing, vol. 3, pp.192–206, Mar. 1994.

[17] T. Sun and Y. Neuvo, “Detail-preserving median based filters in image processing,” Pattern Recognition Letters, vol. 15, pp. 341–347, 1994.

[18] E. Abreu, M. Lightstone, S. K. Mitra, and K. Arakawa, “A new efficient approach for the removal of impulse noise from highly corrupted images,” IEEE Transaction Image Processing, vol. 5, pp. 1012–1025, June 1996.

[19] Z.Wang and D. Zhang, “Restoration of impulse noise corrupted images using long-range correlation,” IEEE Signal Processing Letters, vol. 5, pp.5–8, 1998.

[20] D. Zhang and Z. Wang, “Impulse noise detection and removal using fuzzy techniques,” Electronics Letters, vol. 33, no. 5, pp. 378–379, 1997.