現行工業上使用於電路元件之自動化光學檢測技術主要有以下的困難：一是在使用灰階影像進行電路元件檢測時，難以藉由良好的打光技術獲得清晰的元件輪廓影像；二是在使用彩色影像進行電路元件檢測時，檢測彩色影像中元件輪廓所使用的演算法運算量過大，運算時間過長，不適合應用於工業檢測上。
本研究主要以薄膜電路元件檢測與一般電路版之元件檢測為研究範圍，針對上述現有光學檢測技術發生的困難，分別研發灰階影像之最佳打光取像方式，運算量較小之彩色影像元件輪廓偵測技術，以及在擁有元件清晰輪廓前提下之元件瑕疵檢測演算法。

首先，在薄膜電路元件檢測研究中，利用薄膜電路透光的特性，使用背向打光取得零件輪廓清晰的灰階影像，並針對該影像研發運算量較小的Go Gage檢測法，完成檢測速度較快，且正確性較高的薄膜電路元件的光學檢測方式。

其次，於一般不透光電路版之元件檢測研究中，我們使用電路元件之彩色影像，並利用電路元件的顏色分佈特徵，研發運算量較小的彩色影像最佳化物件分割技術，獲得物件之輪廓，最後結合Go Gage檢測法，完成檢測速度較快，且正確性較高一般不透光電路版之元件的光學檢測。

[1] Kishimoto S. and Kakimori, N. and Yamamoto Y. and Takahashi Y. and Harada T. and Iwata Y. and Shigeyama Y. and Nakao T., “A Printed Circuit Board (PCB) Inspection System Employing the Multi-Lighting Optical System,” 8th IEEE/CHMT International IEMT Conference on Electronic Manufacturing Technology Symposium, pp. 120-129, 1990,
[2] E.R. Davies, “Machine Vision: Theory, Algorithm, Practicalities,” Academic Press, 2nd Edition, pp.103-130.
[3] R.C. Gonzalez and R. E. Woods, “Digital Image Processing,” Prentice Hall, 2002.
[4] M. Sonka and V. Hlavac and R. Boyle, “Image Processing, Analysis, and Machine vision,” PWS Publishing, 1999.
[5] B.K.P. Horn, “Robot Vision,” MIT Press, 1986.
[6] Machuca R. and Phillips, K., “Applications of Vector Fields to Image Processing,” IEEE Trans. Pattern Anal. Machine Intelligence, vol. PAMI-5, pp. 316–329, May 1983.
[7] S.D. Zenzo. “A Note on the Gradient of a Multi-Image,” Computer Vision, Graphics, and Image Processing, vol. 33, pp. 116-125, 1986.
[8] P.E. Trhanias and A.N. Venetsanopulos, “Color Edge Detection using vector order statistics,” IEEE Trans. On Image Proc, Vol.2, no.2 , pp.259-265, April 1993,
[9] P.E. Trahanias and A.N. Venetsanopoulos, “Vector Order Statistics Operators As Color Edge Detectors,” IEEE Trans. Syst., Man,and Cyb., Part B: Cybern., vol. 26, no. 1, pp. 135-142, Feb. 1996
[10] J. Scharcanski and A.N. Venetsanopoulos, “Edge-Detection of Color Images Using Directional Operators,” IEEE Transactions on Circuits and systems for Video Technology, vol. 7, no.2, pp. 397-401, April 1997.
[11] A. Fotinos and G. Economou and S. Fotopoulos, “Use of Relative Entropy in Colour Edge Detection,” Electronic Letters, vol. 35, no. 2, pp.1532-1534, September 1999.
[12] M.J. Swain and D.H. Ballard, “Color Indexing,” International Journal of Computer Vision, vol. 7, no. 1, pp. 11-32, 1999.
[13] J. Wang and K.K. Ma, ” Using Eigencolor Normalization for Illumination-Invariant Color Object Recognition”, PATTERN Recognition, vol. 35, no. 11, pp. 2629-2642, Nov. 2002.
[14] D.M. Tsai and Y.H. Tsai., “Rotation-invariant pattern matching with color ring-projection”, Pattern Recognition vol.35, no. 1, pp. 131-141, January 2002.
[15] R. Alferez and Y.F. Wang, ”Geometric and Illumination Invariants for Object Recognition” IEEE Transactions on Pattern Analysi and Machine Intellicence, vol. 21, no. 6, June 1999.
[16] D.H. Ballard and C.M. Brown, “Computer Vision”, Rainbow-bridge Book Co, pp.33-35.
[17] N. Liu and H. Yan, “Segmentation of Map Image Using Opponent Color Dimensions”, Color Research and Application, vol 21 no. 2 pp. 115-120, April 1996.
[18] P. Green and L. MacDonald, “Colour engineering” Chichester Wiley, 2002.
[19] R.C. Birney and R.C. Teevan, “Instinct,an enduring problem in psychology” Princeton, N.J.,Van Nostrand, 1961.
[20] R.L. Burden and J.D. Faires, “Numerical Analysis” Brooks/Cole, 7th edition.
[21] 彭國軒,“環形編碼與模型比對技術”,清華大學碩士論文，2003.