物件輪廓線的取得在影像處理中佔極重要的角色，且輪廓線取得的準確性與方便性，也是決定一影像處理系統好壞的重要因素。所謂的動態輪廓線模型，係指由系統或使用者給定的初始輪廓線，然後再經由一組牽引的力量將輪廓線形變（deform）至正確的位置，這種取得輪廓線的方法，不但方便而且準確度也很高。
本論文整理各種動態輪廓線模型，並且實作離散動態輪廓線模型(Discrete Dynamic Contour Model)。為了解決初始輪廓線必須接近欲取得物件的問題，我們將圖素（pixel）相連的特性考慮進來成為物件邊線的質量，並且將質量整合進我們的輪廓線模型；對於輪廓線的可疑（或不正確）部份，我們應用評估（evaluation）的方法來偵測與修正。在一系列平面影像的輪廓線自動取得的功能上，我們加入物件比對的機制使得初始輪廓線和物件實際位置不至偏離太遠，減少動態輪廓線出錯的機會。在自動獲得這一系列的輪廓線後，除了可將影像不必要的部分去除，減少儲存所需的空間之外，也有助於立體影像的重建。

A contour plays an important role in image segmentation. A convenient way to obtain accurate contours is one of the key features of a robust image processing system. The Active Contour Model was proposed to segment an object correctly in an effective way. In this model, an initial contour is given first and then deforms according to a set of defined forces to obtain the final result.
In this thesis, we study several different contour models. Among these models, we implement the Discrete Dynamic Contour Model because it is based on a simple structure and its deformation is controlled by basic physical rules. We take the influence of a pixel’s features into consideration (referred to as “mass”) and add this factor into the contour model. In order to eliminate the suspicious (or incorrect) parts of the deformed contour, we make use of an evaluation mechanism to detect them and correct them by adjusting the weighting of different forces in the contour model. In order to solve the problem that the initial contour must be close enough to the segmented object, we also add a mechanism of object matching to extract the contours of some object in a series of images automatically and successfully. After obtaining a series of contours, we can remove the unnecessary part of an image to reduce the required storage space to store region of interest and three-dimensional objects can be reconstructed by these contours.

第1章 導論……………………………………………………………………1
第2章 背景.................................................4
第3章 實作問題與解決方法…………………………………………………10
第4章 系統設計與實作………………………………………………………43
第5章 結果……………………………………………………………………48
第6章 結論……………………………………………………………………52
參考文獻………………………………………………………………………54

[Anthony 97] Anthony Yezzi, Jr., Stayanad kichenassamy, and Arun Kumar, Peter Olver, and Allen Tannenbaum, "A Geometric Snake Model for Segmentation of Medical Imagery", IEEE Transactions on Medical Imaging, Vol. 16, No.2, April 1997.
[AIS+77] C. Alexander, S. Ishikawa, M. Silverstein, N. Jacobson, I. Fiksdahl-King, and S. Angle.
[Canny86] J. F. Canny, “A computational approach to edge detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 8, pp. 679-698, Nov. 1986.
[Ballard 81] D. H. Ballard, “Generalizing the Hough Transform to Detect Arbitrary Shapes”, Pattern Recognition, Vol. 13, No. 2, pp.111-122, 1981.
[Cohen 89] A. L. Yulle, D. S. Cohen, and P. W. Hallinan, "Feature extraction from faces using deformable templates", Proceedings of Computer Vision and Pattern recognition, San Diego, June 1989.
[Cohen 91] Laurent D. Cohen, "Note : On Active Contour Models and Ballons", CVGIP: Image Understanding, Vol. 53, No. 2, March, pp. 211-218,1991.
[FKU77] H. Fuchs, Z. M. Kedem, and S. P. Uselton, “Optimal Surface Reconstruction from Planar Contours,” Commun. Ass. Comput. Machine, Vol. 20, pp. 693-702, Oct. 1977.
[GW93] R. C. Gonzalez and R. E. Woods, Digital Image Processing, Addison- Wesley Publishing Company, 1993.
[Hough62] Milan Sonka, Vaclav Halavac and Roger Boyle, "Image Processing, Analysis and Machine Vision", Chapman & Hall, pp. 149-153.
[KWT88] M. Kass, A. Witkin, and D. Terzopoulos, “Snake: Active Contour Models,” International Journal of Computer Vision, pp. 321-331, 1988.
[LH98] R. S. Lin and Y. C. Hsueh, “Edge Linking by Ridge Tracing,” Proc. Int. Comput. Symp. 1998, Tainan, Taiwan, pp. 166-171, Dec. 1998.
[LT90] Song-Tyang Liu and Wen-Hsiang Tsai, “Moment Preserving Corner Detection,” Pattern Recognition, Vol. 23, No. 5, pp. 411-460, 1990.
[LV95] S. Lobregt and M. A. Viergever, “A Discrete Dynamic Contour Model,” IEEE Trans. on Medical Imaging, Vol. 14, No. 1, pp. 12-24, Mar. 1995.
[MG92] Y. Mahdavieh, and R. C. Gonzalez, Advances in image analysis, SPIE Optical Engineering Press, 1992. （Canny edge detection ）
[MH80] D. Marr and E. C. Hildreth, “Theory of edge detection,” Proc. R. Soc. Lond. , Vol. 207, pp. 187-217, 1980.
[Song 96] Song Chun Zhu and Alan Yuille,"Region Competition:Unifying Snakes, Region Growing, and Bayes/MDL for Multiband Image Segmentation",IEEE Transaction on Pattern Analysis and Machine Intelligence, vol.18, no.9 September, 1996.
[Tagare 97] H.D. Tagare, "Deformable 2-D Template Matching Using Orthogonal Curves," IEEE Transactions On Medical Imaging, Vol. 16, No.1, pp. 108-117, February 1997