臺灣博碩士論文加值系統

隨著單眼相機在消費市場上越來越普遍，使用人數逐年增加，使得數位單眼相機容易出現感光元件染塵（即CCD染塵現象）的問題變得不容忽視。雖然有CCD染塵現象的數位單眼相機可以送往廠商以人工手動清除，不過通常價格昂貴，而且如果傷及CCD，到時候可能更要花一大筆費用來修理，得不償失。最近有一些相機廠商發明「感光元件自我清理架構」，利用壓電元件產生超音波震動，讓粉塵脫落，不過對於黏度較高的粉塵，則效果不彰。

於是有人提出用傳統去雜訊的方法來將影像上的粉塵清除，由於粉塵雜點比一般雜訊要大得多，因此如果只是使用一般中值濾波器將會失敗。另外，也有人提出利用市面上的影像處理軟體，例如Photoshop 的修復筆刷工具與PhotoImapct的修容工具等，來將粉塵拿掉，但是類似這樣的工具，都必須自己手動選取要拿掉的粉塵並自己找材質來填補，因此耗時耗力。而本篇研究的目的則是提出一個能夠自動偵測粉塵的演算法，同時利用影像修補的技術，將影像上令人困擾的粉塵去除，並且維持影像中的材質與線性結構的完整。實驗結果顯示，所提演算法能有效解決數位影像的感光元件染塵問題。

The digital cameras are becoming more and more popular nowadays. Digital SLRs not only allow photographers to use inter-changeable lenses to get different ranges of zoom and depth of field, but also give the users more control, it helps to take a better picture. Recently the number of digital SLR users is rising steadily as the equipments drop in price. However, unlike film cameras, current digital SLRs suffer from a frustrating weakness: sensor dust. It is obvious that the dust can damage the photos seriously. Cleaning dust on sensors is almost universally warned against by camera makers. If we remove the dust directly by the sensor brush, we might scratch or otherwise damage the cover glass over the sensor, therefore are responsible for the cost of repairs. Camera manufacturers have introduced the dust-reduction solution that involves anti-static coatings and vibration-cleaning of the low-pass filter. However, they can not remove the dust particles with high viscosity effectively.

Some photographers propose to correct this problem in software. The traditional noise reduction methods such as median filter do not perform well in removing the dust spots, since the size of the noise in digital photos caused by dust is large. Some image editing software such as Adobe Photoshop and Ulead Photoimpact also provide the healing brush and clone stamp to stamp out the dust specs, one at a time. However, it is a time-consuming and tedious process if we are taking many photos that suffer from this problem. In this study, we develop an automatic spots removal algorithm based on the inpainting technique. We first propose a noise detection algorithm to identify the dust spots, it uses Sobel filter and the process is fully automatic. A fast exemplar-based image inpainting approach is then proposed to fill holes of dust spots in images, it achieves accurate propagation of linear structures. Several examples on real images are given to demonstrate the effectiveness of the proposed method.

圖目錄 viii
表目錄 xi
第一章 前言 1
1.1研究動機與目的 1
1.2論文架構 6
第二章 文獻回顧 7
2.1基於偏微分方程的影像修補演算法 7
2.2材質合成 12
2.3結合偏微分方程與材質合成的演算法 16
第三章 所提之範例影像修補演算法 27
3.1基於範例影像修補演算法 27
3.2快速範例影像修補演算法 33
第四章 自動粉塵偵測 37
4.1 Sobel運算結合擴張運算 37
4.2 同質群體濾波器（peer group filter，PGF） 42
4.3 連通成分萃取運算 45
第五章 實驗結果與討論 50
第六章 結論 58
參考文獻 59

[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. Chan and J. Shen. “Mathematical Models for Local Deter-ministic 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., vol. 4, no. 12, 2001, pp.436-449.
[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(VIIP 2001), 2001, pp.261-266.
[5]A. Telea, “An Image Inpainting Technique Based on the Fast Marching Method,” Journal of Graphics Tools, 2004, pp.25-36.
[6]D. J. Heeger, and J. R. Bergen, “Pyramid-based Texture Analysis/Synthesis,” Proceedings of SIGGRAPH, Aug. 1995, pp.229-238.
[7]J. Portilla, and E. P. Simoncelli, “A parametric texture model based on joint statistics of complex wavelet coefficients,” International Journal of Computer Vision, Oct. 2000, pp.49-70.
[8]J. S. Debonet, “Multiresolution sampling procedure for analysis and synthesis of texture images,” Proceedings of SIGGRAPH, Aug. 1997, pp.361-368.
[9]A. Efros and T. Leung, “Texture synthesis by nonparametric sampling,”in Proc. Int. Conf. Computer Vision, Kerkyra, Greece, Sept. 1999, pp.1033-1038.
[10]L. Y. Wei, and M. Levoy, “Fast texture synthesis using treestructured vector quantization,” Proceedings of SIGGRAPH, July 2000, pp.479-488.
[11]M. Ashikhmin, “Synthesizing natural textures,” in Proc. ACMSymp. Interactive 3D Graphics, Mar. 2001, pp. 217–226.
[12]A. Efros and W. T. Freeman, “Image quilting for texture synthesis and transfer,” in Proc. ACM Conf. Computer Graphics (SIGGRAPH), Aug. 2001, pp.341-346.
[13]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, July 2001, pp.127-150.
[14]V. Kwatra, A. Schodl, I. Essa, G. Turk, and A. Bobick, “Graphcut textures: Image and video synthesis using graph cuts,” ACM Transactions on Graphics (SIGGRAPH 2003), July 2003, pp.277-286.
[15]Q. Wu, and Y. Yu, “Feature matching and deformation for texture synthesis,” ACM Transactions on Graphics (SIGGRAPH 2004), Aug. 2004, pp.364-367.
[16]M. Bertalmio, L. Vese, G. Sapiro, and S. Osher, “Simultaneous structure and texture image inpainting,” IEEE Trans. Image Processing, Volume: 12 Issue: 8 , Aug. 2003, pp.882-889.
[17]J. H. Yamauchi, H. P. Seidel, “Image Restoration Using Multiresolution Texture Synthesis and Image Inpainting,” Computer Graphics International, July 2003, pp.120-125.
[18]I. Drori, D. Cohen-Or, and H. Yeshurun, “Fragment-based image completion,” in ACM Trans. Graphics (SIGGRAPH), vol. 22, San Diego, CA, July 2003, pp.303-312.
[19]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, WI, June 2003, pp.643-650.
[20]P. P. Criminisi, and K. Toyama, “Region Filling and Object Removal by Exemplar-Based Image Inpainting,” IEEE Trans. Image Processing, Vol. 13, No. 9, Sept. 2004, pp.1200-1212.
[21]J. Sun, L. Yuan, J. Jia, and H.-Y. Shum, “Image Completion with Structure Propagation,” ACM Trans. on Graphics (SIGGRAPH 2005), July 2005, pp.861-868.
[22]N. Komodakis, and G. Tziritas, “Image Completion Using Global Optimization,” in Proc. Conf. on Computer Vision and Pattern Recognition(CVPR''06), 2006, pp.442-452.
[23]B. Smolk , R. Lukac , K.N. Plataniotsis , A.N. Venetsanopoulos , and A. Chydzinski, “Fast Technique of Impulsive Noise Removal in Multi-channel Images,” IEEE ISIE, vol. 3, June. 2005, pp. 1267-1272.
[24]吳世傑, “一個有效的彩色影像雜訊去除之混合式向量濾波器演算法”, 中興大學資訊科學所碩士畢業論文, 六月, 2006.