成功大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	蔡典修 Tsai, Tien-Hsiu
論文名稱：	以評估式動態輪廓線模型及知識源為基礎的影像分割方法 Image Segmentation Methods Using Evaluation-Based Active Contour Model and Knowledge Source
指導教授：	陳立祥 Chen, Lih-Shyang
學位類別：	碩士 Master
系所名稱：	電機資訊學院 - 電腦與通信工程研究所 Institute of Computer & Communication Engineering
論文出版年：	2008
畢業學年度：	96
語文別：	中文
論文頁數：	105
中文關鍵詞：	影像分割、輪廓線評估、動態輪廓線模型、膝蓋軟骨、知識源
外文關鍵詞：	image segmentation, contour evaluation, active contour model, Knowledge Source, knee cartilage
相關次數：	點閱：144 下載：4
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

　　醫學影像分割是重建器官三維模型之前的必備工作，但並不是一件容易的工作。本論文中提出的「輪廓線評估系統」、「評估式動態輪廓線模型」與「知識源」其目的就是要協助醫學影像分割工作的進行。
　　輪廓線評估系統是利用相鄰影像之間影像特徵變化不大的特性，將待測輪廓線與參考輪廓線進行分段並比較，以決定其正確性。此機制應用於動態輪廓線模型中，可以幫助其尋找最佳的影像邊緣，提升變形的正確性，協助使用者有效率地繪製器官輪廓線。
　　本論文後半利用影像與目標器官的已知特徵，設計針對該器官的自動化分割機制。我們將這個做法稱為利用「知識源」的影像分割。這部份將以手肘骨骼與股骨軟骨為例，說明其設計過程與實作成果，並且以股骨軟骨的辨識結果進一步進行後續應用，包含軟骨厚度計算、顯示與其他應用。

Medical image segmentation is a necessary task before reconstructing a 3D organ model, but not an easy task. This thesis describes how the Contour Evaluation System, the Evaluation-Base Active Contour Model, and the Knowledge Source are used to segment medical image correctly and efficiently.
The Contour Evaluation System calculates the similarity between the reference contour and the evaluated contour to determine the accuracy of the evaluated contour, because the image features between neighbor images are expectedly similar. This mechanism can help the Active Contour Model to find correct image edges, improve the deformation result, and assist users to draw the organ contours more efficiently.
The Knowledge Source is a mechanism designed to generate organ contours automatically when we have the pre-knowledge about the source images and the target organ. We take the elbow bone and knee cartilage examples to demonstrate the design procedures and implement results. We also make use of the cartilage recognition result for follow-up application, such as cartilage thickness measurement and display.

§  中文摘要  §	I
§  英文摘要  §	III
§  誌 謝  §	V
§  目 錄  §	VII
§  圖表目錄  §	XI
第一章	導論	1
1概述	1
2研究動機與目的	1
3章節提要	2
第二章	研究背景	4
1人體器官三維模型重建(3D RECONSTRUCTION)	4
2影像分割與分析處理方法簡介	5
2.1影像分割方法分類	5
2.1.1 臨界值法（Thresholding）	5
2.1.2 邊緣基礎（Edge-based）	5
2.1.3 區域基礎（Region-based）	6
2.2影像處理分析方法	6
2.2.1	Histogram (影像分析方法)	6
2.2.2	Morphology (影像處理方法)	7
3相關理論簡介	7
3.1輪廓線曲率特徵點(Curvature Feature Points)	7
3.2中央動差值(Central Moments)	9
3.2.1中央動差值使用動機	9
3.2.2中央動差值原理與應用	10
3.3模糊控制模型(Fuzzy Control Model)	12
3.3.1模糊控制模型簡介	12
3.3.2模糊控制模型原理	13
4測試平台：三維物件重建系統（3D BUILDER）	19
第三章	輪廓線評估系統與動態輪廓線模型	21
1輪廓線評估系統(CONTOUR EVALUATION SYSTEM)	21
1.1目的	21
1.2參考式評估的基本構想	22
1.3輪廓線周圍影像取樣	23
1.4輪廓線分段	24
1.4.1競爭型分段	26
1.4.2依據中央動差值與模糊控制模型決定影像特徵差異量	26
1.4.3影像特徵分段完整流程	29
1.5線段對應方式	30
1.6評估與結果表示	33
2評估式動態輪廓線模型	34
2.1目的	34
2.2前處理	37
2.2.1去除影像雜訊	37
2.2.2相關區域截取	38
2.2.3邊緣偵測	38
2.3評估邊緣	40
2.4變形	41
3成果	43
3.1輪廓線評估系統測試結果	43
3.2評估式動態輪廓線模型測試結果	45
第四章	手肘骨骼分割	46
1背景	46
1.1手肘骨骼構造簡介	46
1.2電腦斷層掃描(CT)的影像特徵	48
2影像分割流程	49
2.1自動尋找ROI（region of interest）	49
2.2利用灰階值分割出骨骼部份	52
2.2.1自動取得TBC	52
2.2.2以Threshold方式分割影像	55
2.3以分水嶺法(Watershed)將相連的骨骼分離	57
3影像分割成果	61
第五章	股骨軟骨厚度計算及其應用	65
1背景	65
2影像分割	67
2.1在MIP影像中指定ROI	67
2.2尋找軟骨輪廓線	68
3軟骨厚度計算與3D模型建置	70
3.1準備工作	70
3.1.1判斷內外部	70
3.1.2偵測完整的表面點	72
3.2 厚度計算方法比較	75
3.3 演算法與資料結構	78
3.4 建置3D模型並著色顯示厚度	80
3.5 局部相對厚度	82
4其他應用	87
4.1取得特定位置厚度	87
4.2顯示三方向截面圖	88
4.3 顯示任意角度截面圖與切割3D物件	90
第六章	結論	93
1研究成果	93
2未來發展方向	94
2.1 輪廓線評估系統	94
2.2 評估式動態輪廓線模型	94
2.3 軟骨辨識	94
2.4 局部相對厚度	95
§  參考文獻  §	96
附錄　平行處理機制與效能監視器	99
簡介	99
CLASS DIAGRAM與相關說明	101
效能監視器	102
應用實例	104
作者簡介	105
                                    

[1]: Canny, J. F., "A computational approach to edge detection," IEEE Trans, Pattern Analysis and Machine Intelligence, Vol. 9, pp. 679-698, Nov. 1986
[2]: Chen, Y. C., "An Image Recognition System Based on a Blackboard Architecture," National Cheng Kung University, 2008.
[3]: Deng, S. T., "Surface Construction and Manipulation of 3D Medical Images," National Cheng Kung University, 2007.
[4]: Gonzalez, R. C., & Woods, R. E., "Digital Image Processing," Second Edition, Prentice-Hall Inc., 2002.
[5]: Heuer, F., Sommers, M., Reid III, J. B., and Bottlang, M.,“Estimation of cartilage thickness from joint surface scans: Comparative analysis of computational methods.” In ASME, pages 569–570, 2001.
[6]: Hsu, H. L., "The Application of the Contour Evaluation System on the Medical Images", National Cheng Kung University, 2006.
[7]: Kang, Y., Engelke, K., & Kalender, W. A., "A New Accurate and Precise 3-D Segmentation Method for Skeletal Structures in Volumetric CT Data”, IEEE Trans. Med. Imag., vol. 22, no.5, pp. 586-598, May 2003.
[8]: Kass, M., Witkin, A., & Terzopoulos, D., "Snake: Active Contour Models," International Journal of Computer Vision, pp.321-331, 1988
[9]: Ke, P. Y., "3D Reconstruction of human body system and interactive medical education game," National Cheng Kung University, 2006.
[10]: Lobregt, S., & Viergever, M. A., "A Discrete Dynamic Contour Model," IEEE Trans. on Medical Imaging, Vol. 14, No. 1, pp. 12-24, Mar. 1995
[11]: Lorensen, W. E., & Cline, H. E., “Marching cubes: A high resolution 3D surface construction algorithm,” ACM SIGGRAPH Computer Graphics, v.21 n.4, p.163-169, July 1987
[12]: Lynch, John A., Zaim, S., Zhao, J., Peterfy, C. G., Genant, H. K., "Automating measurement of subtle changes in articular cartilage from MRI of the knee by combining 3D image registration and segmentation," Proc. SPIE Vol. 4322, p. 431-439, Medical Imaging 2001.
[13]: Meyer, F., "Contrast feature extraction." In: J.L. Chermant Editor, Quantitative Analysis of Microstructures in Material Sciences, Biology and Medicine Riederer Verlag, Stuttgart, Germany, 1978.
[14]: Meyer, F., "Color image segmentation." In Proceedings of the International Conference on Image Processing and its Applications, pages 303--306, 1992.
[15]: Mlejnek, M., Vilanova, A., & Gröller, M. E., "Interactive Thickness Visualization of Articular Cartilage," In Proceedings of Visualization 2004, pages 521-527, October
[16]: Niblack, W., "An Introduction to Digital Image Processing," Upper Saddle River, NJ: Prentice-Hall, ch. 5, 1986.
[17]: Ruzon, M. A., Tomasi, C., "Color Edge Detection with the Compass Operator," cvpr, p. 2160, 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'99) - Volume 2, 1999
[18]: Ruzon, M. A., Tomasi, C., "Corner Detection in Textured Color Images," In 7th IEEE International Conference on Computer Vision, Kerkyra, Greece, V. 2, pp. 1039-1045, September 1999
[19]: Ruzon, M. A., Tomasi, C., "Edge, Junction, and Corner Detection Using Color Distributions," In IEEE Transactions on Pattern Analysis and Machine Intelligence, V. 23, No. 11, pp. 1281-1295, November 2001
[20]: Samuel C. Lee, Yiming Wang, & Elisa T. Lee, “Compactness Measure of Digital Shapes”, IEEE, 2004.
[21]: Theodoridis, S., & Koutroumbas, K.,“Pattern Recognition”Second Edition, Elsevier Inc., 2003.
[22]: Wang, L. I., & Greenspan, M., "Validation of Bone Segmentation and Improved 3-D Registration Using Contour Coherency in CT Data", IEEE Trans. Med. Imag., vol. 25, no.3, pp. 324-334, March 2006.
[23]: Yang, C. M., "The Applications of the Automatic Contour Recognition Mechanism on the Medical," National Cheng Kung University, 2007.

校內：2013-08-12公開
校外：2013-08-12公開

簡易檢索 / 詳目顯示

相關論文