自動化檢測系統的技術與設備，其中自動光學檢測(Automated Optical Inspection, AOI)扮演著重要的角色，目前許多廠商都在致力發展檢測的設備，進而取代人力，達到增加產線的效能以及降低開發的成本，但目前的自動光學檢測系統皆採用工業等級的電腦做為主要的運作系統，因而導致成本較高的情況，隨著數位訊號處理器(Digital Signal Processor, DSP)不斷的發展，已達到處理速度快、體積小、低成本與消耗功率低的種種優點，因而本論文的主要目的便是利用DSP作為自動光學檢測系統的運作平台，進而取代使用工業級電腦的自動光學檢測系統，本研究所開發的系統主要利用GigE高解析度攝影機做為擷取影像的攝影機，並傳送至DSP DM6437開發平台進行瑕疵檢測的運算，檢測瑕疵的位置並針對瑕疵作形態的分類，最後透過乙太網路將瑕疵檢測的結果傳輸至人機介面，供使用者做進一步的確認。

Automatic optical inspection, AOI, plays an important role in technique and equipments of automatic inspection system. For the sake of replacing inspecting by human, a lot of manufacturers make every effort to develop inspection equipment. It could increase efficiency of production and reduce the cost. Presently, industrial computers are usually used as the operating system of AOI, leading to higher costs. With the continuous development of Digital Signal Processor (DSP), it becomes faster, smaller, low-cost and low power. The purpose of this paper is to use DSP as the operating system of AOI so as to replace industrial computer. The system of this thesis is adopting high-resolution GigE cameras to capture the image. The GigE camera will transfer the image to DSP DM6437 Evaluation Module for inspecting defects and identifying the type of defects. The result will be transferred to human-computer interface through the Ethernet and then users could do make further confirmation.

參 考 文 獻

[1] W. Y. Wu, M. J. Wang and C. M. Liu, “Automated Inspection of Printed Circuit Boards Through Machine Vision,” Computers in Industry, Vol. 28, No. 2, pp. 103-111, 1996.
[2] Texas Instruments Inc., TMS320DM643x DMP Enhanced Direct Memory Access (EDMA3) Controller, March 2008.
[3] J. P. Serra, Image Analysis and Mathematical Morphology, Academic Press, pp. 115-130, 1982.
[4] J. M. Guo, C. H. Hsia, M. H. Shih, Y. F. Liu and J. Y. Wu, “High Speed Multi-Layer Background Subtraction,” IEEE International Symposium on Intelligent Signal Processing and Communication Systems, pp. 74-79, November 2012.
[5] R. C. Gonzalez and R. E. Woods, Digital Image Processing, Prentice-Hall, New Jersey, pp. 116-123, 2002.
[6] Automated Imaging Association, GigE Vision 2.0 Specification, November 2011.
[7] 劉國偉, “基於GigE視覺之印刷電路板自動光學檢測系統,” 國立台灣科技大學電機工程系碩士論文, pp. 18-87, 2012
[8] Basler Vision Technologies, Installation and Setup Guide for Cameras Used with Basler’s Pylon API, February 2008.
[9] U. Lamping, R. Sharpe and E. Warnicke, Wireshark User's Guide : for Wireshark 1.7, 2011.
[10] Texas Instruments Inc., TMS320C6000 TCP/IP Network Developer’s Kit User’s Guide, June 2003.
[11] Basler Vision Technologies, The Elements of GigE Vision, May 2007.
[12] Basler Vision Technologies, Controlling Packet Transmission Timing with the Interpacket and Frame Transmission Delays on Basler GigE Vision Cameras Application Notes, July 2008.
[13] Basler Vision Technologies, User’s Manual for GigE Camera, July 2011.
[14] R. O. Duda and P. E. Hart, “Use of the Hough Transformation to Detect Lines and Curves in Pictures,” Communications of the Association for Computing Machinery, Vol. 15, No. 1, pp. 11-15, 1972.
[15] T. C. Chen and K. L. Chung, “An Efficient Randomized Algorithm for Detecting Circles,” Computer Vision and Image Understanding, Vol. 63, No. 83, pp. 172-191, 2001.
[16] N. Otsu, “A Threshold Selection Method from Gray-level Histograms,” IEEE Transactions on Systems, Man and Cybernetics, Vol. 9, No. 1, pp. 377-393, 1979.
[17] Texas Instruments Inc., TMS320DM643x DMP Inter-Integrated Circuit (I2C) Peripheral User’s Guide, March 2011.
[18] Spectrum Digital Inc., TMS320DM6437 Evaluation Module Technical Reference, December 2006.
[19] Catalyst Semiconductor Inc., CAT24C256 256-Kb I2C CMOS Serial EEPROM, February 2006.
[20] Spansion Advance Information, S29GLxxxN MirrorBitTM Flash Family, October 2003.