臺灣博碩士論文加值系統

本論文以互動的方式發展一套影像切割的方法。透過人與機器互動式的溝通，使正確的影像邊界能被迅速且正確地萃取出來。改良以往互動式的影像切割方法，使其用途更具效率與實用性。將最佳路徑搜尋的概念套入影像切割問題上，是極具彈性且有挑戰性的作法，而且證實這樣的處理方式，會產生很好的結果。改良方向主要有三個部份，一.限定特殊的搜尋範圍。二.動態規劃的路徑搜尋方法。三.智慧型的最佳路徑修正方法。使用擴散化(dilation)配合骨幹化(skeletonization)的方式，尋找出合適的搜尋範圍。有限制的搜尋範圍，將使搜尋的速度更快，更具效率。動態規劃(dynamic programming)是最佳路徑搜尋的一種方法。搜尋後的結果，不但可以建立起點到終點間的最佳路徑，更可替每個路徑點建立該點到終點的最佳路徑。擁有這樣的優點，我們發展一套雙向最佳路徑修正的方法，使我們在找到唯一的最佳路徑(即邊界)之後，若不滿意其某部份的結果，可以迅速地將不滿意的地方修正為正確的邊界。而在修正的過程中，即時地顯示修正後的結果，以作為修正的依據。由於我們有一主要發展方向是「肺腫瘤的良惡性之辨識」，本論文研究的方法，將應用於協助醫生在肺部的斷層掃瞄圖(512 512灰階圖)中切割腫瘤的邊界，因此對腫瘤的毛邊和支節等特徵，均是我們研究的重點。

摘要 ...................................................... I目錄 ...................................................... II圖目錄 ................................................... IV表目錄 ................................................... VI第一章 緒論 ............................................. 11.1 前言 ........................................ 11.2 研究動機 .................................... 21.3 論文架構 .................................... 5第二章 影像區域耗費值萃取 .............................. 62.1 拉普拉斯交零點值(Laplacian zero-crossing cost) .. 72.2 梯度量值(Gradient magnitude cost) ...............112.3 梯度方向值(Gradient direction cost) ..............112.4 證實特徵值的可行性 ..........................142.4.1 驗證LZC值 ...........................142.4.2 驗證GM值 ...........................162.4.3 驗證GD值 ............................182.4.4 驗證ILC值 ...........................19第三章 以動態規劃求解最佳路徑 ...........................213.1 基本概念 .....................................213.2 演算法 .......................................223.3 動態規劃流程 .................................34第四章 半人工影像邊界擷取 ...............................364.1 標定搜尋區域 ................................364.1.1 擴散化(Dilation) ......................374.1.2 骨幹化(Skeletonization) ................384.1.3 區塊化(Labeling Algorithm) ............404.1.4 標定搜尋範圍 ........................414.2 動態路徑搜尋 ................................424.2.1 完整路徑搜尋 .........................434.2.2 最佳路徑的修正 .......................43第五章 測試效果 .........................................505.1 基本圖形測試 ................................505.2 一般影像圖形測試 ............................565.3 醫療影像斷層掃描圖形測試 ....................59第六章 結論 .............................................64參考文獻 .................................................66

Amini, A.A., Weymouth, T.E., and Jain, R.C., 1990, "Dynamic Programming for Solving Variational Problems in Vision,"IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 12, pp. 855-867.Cohen, L.D., and Kimmel, R., 1996, "Minimum for Active Contour Models: A Minimal Path Approach,"Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 666-673.Falcao, A.X., Udupa, J.K., Samarasekera, S., and Hirsch, B.E., 1996, "Steered Image Boundary Segmentation,"Proceedings of the SPIE-Medical Imaging: Image Processing, Newport Beach, CA, Vol. 2710, pp. 278-288.Falcao, A.X., Udupa, J.K., Samarasekera, S., and Sharma, S., 1998, "Steered Image Segmentation Paradigms: Live Wire and Live Lane,"Graphical Models and Image Processing, Vol. 60, pp. 233-260.Fleck, M.M., 1992, "Widths Yield Reliable Finite Differences,"IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, pp. 412-429.Geiger, D., Gupta, A., Costa, L.A., and Vlontzos, J., 1995, "Programming for Detecting, Tracking, and Matching Deformable Contours,"IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 17, pp. 294-302.Haralick, R.M., and Shapiro, L.G., 1992, Computer and Robot Vision, Addison-Wesley Publishing Company.Kass, M., Witkin, A., and Terzopoulos, D., 1987, "Contour Models,"Proceedings of the First International Conference on Computer Vision, pp. 259-268.Kirk, D.E., 1985, Optimal Control Theory, University Book Publishing Company.Marr, B.D., and Hildreth, E., 1980, "of edge detection,"Proc. R. Soc. London. Ser. B: Biol. Sci. 207, No. 1167, pp. 187-217.Mortensen, E.N. and Barrett, W.A., 1998, "Segmentation with Intelligent Scissors,"Graphical Models and Image Processing, Vol. 60, pp. 349-384.Mortensen, E.N., Morse, B., Barrett, W.A., and Udupa. J.K., 1992, "Boundary Detection Using "Wire"Two-Dimensional Dynamic Programming,"IEEE Proceedings of Computers, pp. 191-198.Parker, J.R., 1997, Algorithms for Image Processing and Computer Vision, Wiley Computer Publishing.Udupa, J.K., and Samarasekera, S., and Barrett, W.A., 1992, "detection via dynamic programming,"Proceedings of the SPIE: Visualization in Biomedical Computing, Vol. 1808, pp. 33-39.