臺灣博碩士論文加值系統

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.

目 錄
摘 要 I
Abstract II
目 錄 III
圖 索 引 VII
表 索 引 XII
第一章 緒論 1
1.1 研究動機與目的 1
1.2 研究方法 2
1.3 論文架構 3
第二章 系統架構 5
2.1 影像擷取程序 6
2.2 定位點計算程序 8
2.3 樣板與檢測門檻值建立程序 9
2.4 瑕疵檢測程序 9
2.5 瑕疵型態分類程序 10
2.6 人機介面網路傳輸程序 11
2.7 硬體規格與配置 12
第三章 數位影像擷取 19
3.1 攝影機連線與參數設定 19
3.1.1 GigE Vision網路模型 19
3.1.2 GVCP與GVSP封包格式 20
3.1.3 攝影機連線方法 23
3.1.4 攝影機參數設定 24
3.2 攝影機影像接收 26
3.2.1 EDMA3影像資料排序[2] 26
3.2.2 Ping-Pong Buffer架構 29
3.2.3 影像封包確認與重傳機制[12,13] 30
第四章 定位點計算與檢測門檻值建立 31
4.1 定位點計算程序 31
4.1.1 YCr二值化 32
4.1.2 形態學雜訊濾除 34
4.1.3 XY投影法與計算定位點 35
4.2 檢測門檻值建立 37
4.2.1 多層式灰階樣板比對法之門檻值建立方法 37
4.2.2 精細層門檻值建立 38
4.2.3 粗糙層門檻值建立 43
第五章 瑕疵檢測與型態分類 45
5.1 多層式灰階樣板比對法 45
5.1.1 粗糙層比對 46
5.1.2 精細層比對 47
5.2 線路與焊墊二值化樣板比對法 52
5.2.1 線路二值化影像萃取 52
5.2.2 焊墊二值化影像萃取 55
5.2.3 二值化影像樣板比對 56
5.3 線路與焊墊二值化與多層式灰階樣板比對法比較 61
5.4 瑕疵型態分類 64
5.4.1 建立灰階值範圍 64
5.4.2 萃取二值化影像 67
5.4.3 瑕疵型態分類法則[1] 69
第六章 DM6437 EVM周邊模組 71
6.1 I2C EEPROM[17,18] 71
6.1.1 I2C匯流排介面 71
6.1.2 I2C資料讀寫 73
6.2 Flash燒錄 74
6.2.1 Flash燒錄方式[20] 74
6.2.2 透過人機介面進行Flash燒錄 77
第七章 系統實現與效能比較 81
7.1 人機介面 81
7.1.1 人機介面網路傳輸架構 81
7.1.2 人機介面配置與功能介紹 86
7.2 系統實現 87
7.3 系統執行效能 91
7.4 系統效能比較 93
7.4.1 時間效益比較 93
7.4.2 檢測結果比較 96
第八章 結論 98
8.1 研究成果 98
8.2 未來發展 101
參 考 文 獻 102

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.