現今產品的製造，在CAD/CAM的快速發展下，隨著設計製造技術的提升，產品的複雜度亦大大的增加，產品之檢測發展更需要隨著設計製造的腳步而進步，在影像檢測已逐漸普遍發展的今日，使用影像作為檢測方法已相當普及，本研究將CAD系統與影像檢測作結合，以CAD輔助之方法，自動化影像檢測之步驟。
由於CAD輔助之故，影像檢測可將檢測過程自動化，減少重覆操作之困擾，節省人力以及時間。由於CAD與影像系統之座標系不同，本研究先經由定位方法得到兩不同系統之座標轉換關係，使得兩者資料可正確對應後，再由檢測規劃之步驟，設定欲檢測之元件與項目，據此對影像進行檢測，影像資料經過影像技術處理，可得所需之輪廓邊界點群，將點群與CAD相對應之元件分析比對進行公差分析，便可得所需檢測結果。

The complexity of product manufacturing increases because of the faster development of CAD/CAM and the higher techniques of manufacturing on the present day. The technique of inspection have to improve to keep up with the development of manufacturing. It is general to use image inspection as a method of inspection. This work combine the CAD system and the image inspection system to simplify the steps of image inspection by using CAD system.
The steps of image inspection could be automated by CAD aiding to decrease repeated operation steps and to save manpower and time. This work have to obtain the coordinate transformation by registration to ensure the data between two system could correspond correctly because the coordinate between CAD system and image system is different. Then we can choose the tolerance items and inspected elements and proceed image inspection by setting inspection plan. In the same time, we can obtain the outline point group from the image using image process techniques. Finally, we get the inspection results by analyzing the tolerance of image point groups based on corresponding CAD elements.

1.R. M. Haralick, “Pose Estimation from Corresponding Point Sets”, Machine Vision for Inspection and Measurement, New York, 1989
2.P. J. Besl, N. D. McKay, “A Method for Registration of 3D Shapes”, IEEE transactions on Pattern Analysis and Machine Intelligence, Vol. 14, No. 2, 1992,pp.239-256
3.K. S. Arun, T. S. Huang, S. D. Blostein, “Least-Squares Fitting of two 3-D Point Sets”, IEEE transactions on Pattern Analysis and Machine Intelligence, Vol. 9, No. 5, 1987,pp.698-700
4.Y. Chen, G. Medioni, “Object Modeling by Registration of Multiple Range Images”, Image and Vision Computing, Vol. 10, No.3, 1992, pp. 145-155
5.T. Masuda, “A Robust Method for Registration and Segmentation of Multiple Range Images”, Computer Vision and Image Understanding, Vol. 61, No.3, 1995, pp. 308-324
6.H. J. Pahk, W. J. Ahn, “Precision Alignment Technique for Parts Having Thin Features Using Measurement Feedback Iterative Method in CAD/CAI Environment”, Int. J. Mach. Tools Manufact. Vol. 36, No.2, 1996, pp. 217-227
7.E. Capello, Q. Semeraro, ”The Effect of Sampling in Circular Substitude Geometrics Evaluation”, Int. J. Mach. Tools Manufact, Vol. 39, No.1, 1999, pp. 55-85
8.H. T. Yau, C. H. Menq, “A Unified Least Squares Approach to the Evaluation”, Quality Assurance Through Integration of Manufacturing Processes and Systems, PED-Vol. 56, ASME 1992
9.Louis-Paul Rives, “Some Linear Models for Estimating the Motion of Rigid Bodies with Applications to Geometric Quality Assurance”, Theory & Methods Vol. 442, No. 93, 1998, pp. 632-642
10.李啟銘, “公差計算中最佳嵌合之不準度分析”, 國立中正大學機械工程研究所碩士論文, 1996
11.G. Moroni, W. Polini, Q. Semeraro, “Knowledge Based Method for Touch Probe Configuration in an Automated Inspection System”, Journal of Materials Processing Tech, 1998, pp. 153-160
12.呂建豪, “智慧型虛擬三次元量測系統之發展”, 國立中正大學機械工程研究所碩士論文, 2000
13.胡哲源, “掌握 Visual C++ MFC 程式設計與剖析”, 文魁, 2000
14.位元文化研究室, “精通視窗程式設計-適用Visual C++ 6.0版”, 文魁, 1999