臺灣博碩士論文加值系統

在製造工業自動化系統中，電腦視覺系統的彈性與直接使其在工業自動化
中深具發展的潛力。因此，如何發展一個具工業應用價值的電腦視覺系統架構實具有其挑戰性。
在本論文中，我們對文獻中以傳統的電腦視覺系統架構發展的視覺系統和以CAD資料為基礎的
電腦視覺系統架構做簡單扼要的介紹，並以工作效能為基礎，討論其優缺點。
而有鑑於CAD視覺系統的缺點，我們以傳統電腦視覺架構為出發點，結合2D辨識系統
和3D物體定位系統來發展一套具有工業實用價值的視覺系統，並以小型直流馬達的組裝工作
來驗證此系統的實用性。
在實驗中，我們以一些測試影像來驗證我們系統的效能，並討論系統辨識錯誤的結果與
發生的原因，進而提出改進的方法與未來的研究方向。

It is well known that the industriris automation is necessary for an enterprise to
increase their profits and also provides stability and reliability for its products. The computer
vision system is the most feasible, straighforward and potential system in the automation.
Hence, how to develop a computer vision system which is valuable to industries is a challenging research area.
In this thesis, we introduced the traditional computer vision system and CAD-based computer vision system in the literature.
We also pointed out the shortages and advantages of both two systems. We use the traditional computer vision system as a basis
, combine 2D object recognition and 3D object positioning system to develop a vision system structure which is valuable to industries automation.
Furthermore, we took the assembly task of small DC motor as an example to prove the value of our vision system.
In experiments, we conducted several experiments to verify our system''s performance. According to the experimental results,
we discussed the results of wrong recognition, and the reasons to result in the wrong recognition. Moreover, the
future work and directions are also mentioned.

1 簡介
1.1 動機與目的
1.2 文獻回顧
1.3 論文結構
2 視覺系統架構
2.1 設計構想
2.2 設計規格
2.3 系統架構與特色
2.4 系統軟體規劃
3 系統功能之詳細介紹
3.1 影像處理
3.2 物體之三度空間定位
3.3 資料庫建立
3.4 物體辨識
4 視覺系統架構在小型直流馬達零組件上之實現
4.1 實驗環境
4.2 實驗結果
5 結論
附錄 系統外觀與功能簡介
參考文獻

[1] Y.C. Kim and J. K. Aggarwal, ''Positioning three-dimensional objects using stereo images'''', IEEE Trans. Robotics and Automation, vol. RA-3, no. 4, pp. 361--373, 1987.
[2] N. Y. Chen, J. R. Birk, and R. B. Kelley, ''Estimating workpiece pose using the feature points method'''', IEEE Trans. Automated Control, vol. AC-25, no. 6, pp. 1027--1041, 1980,
[3] C. Hansen and T. C. Henderson, ''CASGD based computer vision'''', IEEE Trans. Patt. Recog. and Mach. Intelli., vol. 11, no. 11, pp. 1183--1193", 1989.
[4] A. Tremeau and Nathalie Borel, ''A region growing and merging algorithm to color segmentation'''', Pattern Recognition, vol. 30, no. 7, pp. 1191--1203, 1997,
[5] T. Pavlidis and Y. T. Liow, ''Integrating region growing and edge detection'''', IEEE Trans. Patt. Recog. and Mach. Intelli., vol. 12, no. 3, pp. 225--233., 1990.
[6] Y. L. Chang and X. Li, ''Fast image region growing'''', Image and Vision Computing, vol. 13, no. 7, pp. 559--571, 1995.
[7] S. B. Maraphane and M. M. Trivedi, ''Region-based stereo analysis for robotic applications'''', IEEE Trans. Systems, Man and Cybernetics, vol. 19, no. 6, pp. 1447--1464, 1989.
[8] C. S. Chen and Y. P. Hung and C. C. Chiang and J. L. Wu, ''Range data acquision using color structured lighting and stereo vision'''', Image and Vision Computing, vol. 15, pp. 445--456, 1997.
[9] R. Hoffman and H. R. Keshavan and F. Towfiq, ''CAD-driven machine vision'''', IEEE Trans. on Systems, Man, and Cybernetics, vol. 19, no. 6, pp. 1477 --1488, 1989.
[10] R. Nevatia and K. R. Babu, ''Linear Feature Extraction and Description'''', Computer Vision, Graphics and Image Processing, vol. 13, no. 257--269, 1980.
[11] P. J. Flynn and A. K. Jain, CAD-Based Computer Vision: From CAD Models to Relational Graphs, IEEE Trans. Patt. Recog. and Mach. Intelli, vol. 13, no. 2, pp. 114-132, 1991.
[12] R. C. Bolles and P. Horand, ''3DPO: A Three-Dimensional Part Orientation System, The International Journal of Robotics Research, vol. 5, no. 3, pp. 3--26, 1986.
[13] P. J. Besl and R. C. Jain, ''Three-Dimensional Object Recognition'''', ACM Computing Survey, vol. 17, no. 1, pp. 79--145, 1985.
[14] S. A. Dudani and K. J. Breeding and R. B. Mcghee, ''Aircraft identification by moment invariants'''', IEEE Trans. Computer,
vol. c-26, no. 1, pp. 39--45, 1977,
[15] N. Ayache and O. D. Faugeras, ''HYPER : A new approach for the recognition and positioning of two-dimensional objects'''',
IEEE Trans. Patt. Recog. and Mach. Intelli, vol. PAMI-8, no. 1, pp. 44-54, 1986.
[16] M. Yachida and S. Tsuji, ''A versatile machine vision system for complex industrial parts,'''' IEEE Trans. Computer, vol. c-26, no. 9, pp. 882--894, 1977.
[17] R T. Chine and C. R. Dyer, ''Model-based recognition in robot vision'''', ACM Computing Survey, vol. 18, no. 1, pp. 67--108, 1986.
[18] W. A. Perkins, ''Model-based system for complex industrial parts'''', IEEE Trans. Computer, vol. c-27, no. 2, pp. 126--143, 1978.
[19] S. T. Barnard and M. A. Fischler, ''Computational stereo'''' , ACM Computing Survey, vol. 14, no. 4, pp. 553--572, 1982.
[20] U. R. Dhond and J. K. Aggarwal, ''Structure from stereo -- a review'''', IEEE Trans. Patt. Recog. and Mach. Intelli, vol. 19, no. 6,
pp. 1489--1510, 1989.
[21] G. Medioni and R. Nevatia, ''Segment-based stereo matching'''', Computer Vision, Graphics and Image Processing, vol. 31, pp. 2--18, 1985.