醫學影像辨識是一件頗為複雜的工作，必須結合影像處理、電腦圖學及解剖學等眾多相關領域的知識才能完成。在本論文中我們希望可以將辨識的結果經由評估修正，以提供醫學或是教學上之輔助。
　　影像辨識方面，建立在我們已發展的「以黑板架構基礎之互動式影像辨識系統」之上。而影像辨識的結果，我們採用描述物體外圍的輪廓線來表示。因此，在影像結果評估方面，我們發展了一套「輪廓線評估系統」。此輪廓線系統除了可利用辨識出來的器官輪廓線及其原始影像，作一成果優異性的評估，也可以處理來自「動態輪廓線模型系統」產生的邊緣線段，並將評估的結果回饋給該系統，以其對器官輪廓線或邊緣線段作修正，而得到最佳辨識之結果。
　　而辨識、修正後的器官輪廓線，我們除了透過「以輪廓線為主的三維物件重建系統」重建出該器官的三維模型，也利用一套「切面伺服器」展現輪廓線評估修正後的成果。

　The recognition of a medical image is a complex task. We need to integrate the knowledge of image preprocessing, computer vision and anatomy to complete the task. In this thesis, we hope to evaluate the result of image recognition, and correct it. It will help the user to understand more about the organ in a variety of the applications in medicine or education.
　In the part of image recognition, we develop some knowledge sources on a specific segmentation system, Mirac Viewer. We use the contour that used to describe the outline of an object to represent the results of the recognition. Therefore, we develop a “Contour Evaluation System” for evaluation of these recognition results. This evaluation system uses not only the contours and original image, but the edges produced from Active Contour Model system to do a series of evaluations. We will provide information adequately to the Active Contour Model system, and then modify all these contours.
　We use another system named 3DBuilder to reconstruct the 3D organ with the recognized or modified contours. Besides, we also use the Cross-Section Server to represent the final contours.

[1] Chun-Lung Lin, “An Interactive Image Recognition System Based on A Blackboard Architecture”, National Cheng Kung University, 2003
[2] Yu-Jen Lin, “An Active Contour Model and Its Applications in Medical 3D Imaging”, National Cheng Kung University, 2003
[3] Jian-Fu Lin, “A Contour Evaluation System and Its Application in Medical Image Segmentation”, National Cheng Kung University, 2004
[4] Chia-Chen Chang, “An Active Contour Model and Its Applications in Medical 3D Imaging”, National Cheng Kung University, 2005
[5] Richard Hartley, and Andrew Zisserman, “Multiple view geometry in computer vision”, Cambridge University Press, 2000
[6] Bjorn Johansson, “A survey on: Contents Based Search in Image Databases”, Linkoping University
[7] Luomin Gao, David G. Heath, Brian S. Kuszyk, Elliot K. Fishman, “Automatic liver segmentation technique for three-dimensional visualization of CT data”, Radiology, Vol. 201, pp. 359-364, 1996
[8] Y. J. Zhang, “A survey on evaluation methods for image segmentation”, Pattern Recognition, Vol. 29, No. 8, pp.1335-1346, 1996
[9]: Dengsheng Zhang and Guojun Lu, “A Comparative Study on Shape Retrieval Using Fourier Descriptors with Different Shape Signatures”, Monash University
[10] Kunttu, I., Lepistö, L., Rauhamaa, J. & Visa, A., “Multiscale fourier descriptor for shape-based image retrieval”, 17th International Conference on Pattern Recognition (ICPR), Vol. 4, pp. 23-26, 2004
[11] Djemel Ziou, and Salvatore Tabbone, “Edge Detection Techniques An Overview”, International Journal of Pattern Recognition and Image Analysis ,1998
[12] Michael J. Ackerman, “Accessing the Visible Human Project”, D-Lib Magazine, The magazine of the digital library forum, 1995, http://www.dlib.org/dlib/october95/10ackerman.html
[13] Vikram Chalana and Yongmin Kim, “A methodology for evaluation of boundary detection algorithms on medical images”, IEEE Trans. on medical imaging, Vol. 16, No. 5, pp. 642-652, October 1997
[14] Avinash C. Kak, and Malcolm Slaney, “Principles of computerized Tomographic imaging”, IEEE Press, 1987