製造印刷電路板通常需要多於50個步驟,而建立一個有效率的電路板自動檢測系統是刻不容緩的工作,它能提供客觀與高品質檢測系統以取代過去人工檢測的方式。本論文完成印刷電路板元件檢測前端步驟之研究,首先將灰階PCB電路圖以類神經網路演算法將元件部份與銅膜部份分離,再以Moganti提出搜尋電路元件的修正型演算法萃取出元件,其目的是以比對的方式比較參考電路與待測電路,如此便能找出有瑕疵的元件,最後實現修正型類神經演算法(GLVQ)硬體電路。

It usually needs more than 50 process steps to fabricate a printed circuit board , so it is important to set up an effective automatic visual system to test the PC board. The system can provide subjective and high quantitative assessment and it takes the role of tranditional,i.e. artificial operation. The paper implements the first step of automatic visual system. Firstly,the elements and mold of the gray level PCB image are separated by neural network algorithm.Secondly,the basic patterns of the PCB image are extracted by using modified Moganti algorithm. By comparing the reference board with the test board, we can find the defective components.Finally,a modified GLVQ neural network chip has been developed.

[1] M. Moganti and F. Ercal, “Automatic PCB inspection algorithms: A survey,” Computer Vision and Image Understanding, vol. 63, no. 2, March, pp. 287-313, 1996.

[2] M. Moganti, “Segmentation of printed circuit board images into basic patterns,” Computer Vision and Image Understanding, vol. 70, no. 1, April, pp. 74-86, 1998.

[3] M. Moganti, “A subpattern level inspection system for printed circuit boards,”Computer Vision and Image Understanding, vol.70,no.1,April,pp.51-62, 1998.

[4] J. J. Hong, K. J. Park, and K. G. Kim, “Parallel processing machine vision system for bare PCB inspection,” Proc. 24th Annu. Conf. IEEE Industrial Electronics Society, vol. 3, pp. 1346-1350, 1998.

[5] Tsunekawa, Hisashi,” Latest image evaluation systems aid efforts for product quality,” Journal of Electronic Engineering, vol. 29, no. 306, pp. 72-77, 1992

[6] K. Tomordi, P. Foldesy, and P. Szolgay, “ On the chip implementation of analogic algorithms for optical detection of some layout errors of printed circuit boards,” Proc. 5th Int. Conf. Cellular Neural Networks and Their Applications Proceedings, pp.162-168, 1998.

[7] J. H. Koo and S. I. Yoo, “ A structural matching for two-dimensional visual pattern inspection,” Proc. IEEE Int. Conf. Systems, Man, & Cybernetics, vol. 5, pp. 4429-4434, 1998

[8] S.H. Guz and L. Onural, “An automated system for design-rule-based visual inspection of printed circuit boards,” Proc. IEEE Int. Conf. Robotics and Automation, vol.3, pp. 2696-2701, 1991

[9] A.M. Darwish and A. K. Jains “A rule based approach for visual pattern inspection” IEEE Trans. Patt. Anal. & Mach. Intell., vol. 10, no. 1, pp. 56-68, Jan. 1988

[10] M. H. Tatibana and R. de A. Lotufo, “Novel automatic PCB inspection technique based on connectivity,” Proc. X Brazilian Symposium on Computer Graphics and Image Processing, pp. 187-194, 1997.

[11]鄭智仁,“使用有號數字系統加法器設計快速浮點乘加單元”,
碩士論文,逢甲大學資訊工程學系碩士班,2001.

[12]葉怡成,“類神經網路模式應用與實作”,儒林圖書有限公司,台北,1993

[13] S.Y. Huang, K.S. Cheng, and C.-W Mao, ”An Unsupervised Gray-Level-Based LVQ Neural Network for PCB Image Segmentation,” Proceedings of the IASTED international Conference on Visualization, Image, and Image Processing, pp. 472 – 476, Sept. 2001.

[14] S. Y. Huang, K.S. Cheng, C.W. Mao, “Basic Patterns Extraction for Printed Circuit Board Images Analysis,” the International Conference on Computer Vision, Pattern Recognition & Image Processing (CVPRIP'2002), Proceedings, 6th Joint Conference on Information Science, March 8-13, 2002, USA. pp. 769—772.

[15] J.-S. Lin, K.-S. Cheng, and C.-W. Mao, “ A fuzzy Hopfield neural network for medical image segmentation,” IEEE Trans. Nuclear Science, Vol. 43, No. 4, pp. 2389-2398, August, 1996.
[16]林灶生,“數位影像處理實務-使用C語言”,松崗電腦圖書資料股份有限公司,台北,1980
[17] C.W.Mao,S.Y.Huang,C.H.XU*,“FPGA Implementation for a novel bare PCB inspect algorithm based on block level,”The 2002 VLSI Design/CAD Symposium