本研究主旨為發展一套應用於表面黏著型發光二極體(Surface Mount Device Light Emitting Diodes, SMD LED)的自動光學檢測系統，主要檢測發生在SMD LED的二維混料及白殼瑕疵以及三維立碑瑕疵。
在檢測混料瑕疵方面，採用梯度運算子變化指標檢測混料瑕疵的誤判率為4.37%，漏檢率為7.5%、準確率高達94.05%，平均檢測時間為12.97ms。而在白殼瑕疵檢測方面，本研究提出新的灰階度相關係數指標作白殼情況判斷，其誤判率為5.15%，漏檢率為11.34%，準確率為91.75%，平均檢測時間為10.95ms。
三維檢測則沿用二維平面取像設備，其優點為方法，結構簡單，節省成本，而經自行開發的三維檢測系統檢測量測出元件立碑角度，實驗數據結果分析，與元件立碑角度實際情形相比，平均誤差4.51%，平均檢測時間為8.05ms。
本文所提出的系統不僅能快速、精確、且穩定地檢測出二維混料以及白殼瑕疵，更進一步的可檢測出平面取像無法進行三維瑕疵。使用不同指標做判斷，使整個檢測系統更趨於人工智慧化。

This research is to develop an auto optical inspection system for surface mount device light emitting diodes. The principal purpose is to inspect SMD LED for 2D defects which are mixed-material and resin-tearing and for3D defect which is tombstone.
In terms with mixed-material inspection, using the count of gradient operator to recognize LED chip. The false alarm rate is 4.29% and misdetection rate is 7.19%. It successfully detects defects with accuracy up to 94.24%. The average computation time is 12.97 ms. In terms of resin-tearing inspection, the research uses the gray scale correlation for SMD LED image registration. The false alarm rate is 5.15% and misdetection rate is 11.34%. The accuracy is up to 91.75%. The average computation time is 10.95 ms.
3D defect continues to use 2D view finder. The advantage of this structure is simple and cost-saving. The investigation which is inspected by the 3D system, comparing with real situation, the average measurement deviation is 4.51%. The average computation time is 8.05 ms.
This propose of this system is not only to inspect 2D quickly, precisely and steady, but also to inspect 3D flaws which is hard to detect, and make the wole detective system more artificially-intelligent.

目錄
論文審定書 ……………………………………………………………………………. i
致謝 …………………………………………………………………………………… ii
中文摘要 ……………………………………………………………………………... iii
英文摘要 ……………………………………………………………………………... iv
目錄 …………………………………………………………………………………… v
圖次 …………………………………………………………………………………. viii
表次 ………………………………………………………………………………...... xii
第一章 緒論 ………………………………………………………...…………….….. 1
1.1 前言 ……………………………………………………………………... 1
1.2 自動光學檢測(AOI)基本簡介 …………………………………….…… 2
1.3 研究動機 ………………………………………………………………... 4
1.4 研究目的 ……….………….…..………………………………………... 4
第二章 文獻回顧 …………………………..……………………………………….... 5
2.1 二維瑕疵檢測架構 …………………...……..…………….………….… 5
2.1.1 光源照明方式 ………………………..…..………….…………... 5
2.1.2 系統取像方式 ……………….………..…..………….………….. 9
2.2瑕疵檢測方案探討 …………………………………………………..… 11
2.2.1 模板比對法 …...……………………….……..………………… 11
2.2.2 條件判斷法 .………………………….……..………………..… 13
2.3 三維瑕疵檢測架構…………………..………..….……………….….… 13
2.3.1 被動式光源 …………………………….….…………………… 13
2.3.1.1 雙目視覺法 …………………………...…………..…… 14
2.3.1.2 單目視覺法 ……………………………….…………… 15
2.3.2 主動式光源 ……………………………………….………….… 17
2.3.1.1 結構光法 ………………………………….…………… 17
2.3.1.2 白光干涉法 ………………………………….………… 19
2.4 小結…………………..………..….……………….………………….… 20
第三章 SMD LED檢測系統之設計規劃………...………….……………………… 21
3.1 SMD LED檢測項目 …………………………....……………………… 21
3.2 影像前處理 …………………………………….……………………… 24
3.2.1影像基本概念 …………………………………………………… 24
3.2.2 影像校正與定位 ………….…………….……………………… 26
3.2.3 影像強化 ……………………….………….…………………… 30
3.2.4 影像ROI處理 ………..…....…………………….……………… 32
3.3 二維瑕疵混料檢測設計 ……………………………….……………… 32
3.3.1 梯度運算子指標 ……………………………………..………… 32
3.3.2 混料檢測流程 …………………………………………..……… 34
3.4 二維瑕疵白殼不良檢測設計 ………………………….……………… 36
3.4.1灰階影像相關度指標 …………………………………………… 36
3.4.2 白殼檢測流程 …………………………………………..……… 39
3.5 三維瑕疵立碑檢測設計 ……………………………………….……… 41
3.5.1 SMD LED 白殼長度量測 ……………………………………… 41
3.5.2 SMD LED 立碑檢測流程 ……………………………………… 44
第四章 SMD LED檢測系統實現與驗證 ..…….…………………………………… 45
4.1檢測系統設置 ……….....…………………………………………….… 45
4.1.1 光源照明分析 ……....……………………………….….……… 46
4.2.2 影像擷取系統 ……………………………………..…………… 49
4.2 系統整合軟體 ………………………………………………….……… 50
4.3 二維瑕疵混料檢測實驗結果 ……………………….………………… 51
4.4 二維瑕疵白殼檢測實驗結果 …………………….…………………… 53
4.5 三維瑕疵立碑檢測實驗結果 ……………………….………………… 55
第五章 結論與未來展望 ………………………………………….………...……… 59
5.1 結論 ……………………………………………….…………………… 59
5.2 未來展望 ………………………………………………………………. 60

參考文獻 ………………………………………………………..…………………… 62
附錄一 系統設備規格……………………..………………………………………… 68
附錄二 二維混料瑕疵檢測數據……………………..……………………………… 70
附錄三 二維白殼瑕疵檢測數據……………………………..……………………… 80

[1] Gong Yunxin, “Research and development of automatic screw-parameters tester”, Electronics and Optoelectronics (ICEOE), 2011 International Conference on , vol. 1, pp. 320 - 323, 2011
[2] Du W.Y., Dickerson S.L., “Passive component inspection using machine vision’’, Multichip Modules and High Density Packaging, 1998. Proceedings. 1998 International Conference on , pp. 74 - 79, 1998
[3] Der-Baau Perng, Cheng-Chuan Chou, Wei-Yu Chen, “ A novel vision system for CRT panel auto-inspection ’’, Mechatronics, 2005. ICM '05. IEEE International Conference on , pp. 622 - 625, 2005
[4] Yung-Cheng Wang, Jui-Chang Lin, Shih-Fong Chiu, “ The automatic image inspection system formeasuring dimensional parameters of a saw blade”, Control and Automation (ICCA), 2010 8th IEEE International Conference on , pp.1557 - 1561, 2010
[5] Shih-Feng Chen, “An Optical Inspection System for the Solder Balls of BGA using Support Vector Machine Classification’’, Machine Learning and Cybernetics, 2007 International Conference on , vol.5, pp. 2853 - 2858, 2007
[6] Pang G.K.H., Ming-Hei Chu, “Automated optical inspection of solder paste based on 2.5D visual images’’, Mechatronics and Automation, 2009. ICMA 2009. International Conference on , pp.982 - 987, 2009
[7] Jung-Hun Kim, Suk Ahn, Jae Wook Jeon, Jong-Eun Byun, “A High-Speed High-Resolution Vision System For The Inspection Of TFT LCD”, Industrial Electronics, 2001. Proceedings. ISIE 2001. IEEE International Symposium On , vol. 1, pp. 101 - 105, 2001
[8] W.Lutz, G.Holzmuller, G. Steinwender, E.S. Hochmair, “Fast Measuring of Solid Angles by Means of CCD Line Scan Camera with Analytically Rectified Optics”, Engineering in Medicine and Biology Society, 1994. Engineering Advances: New Opportunities for Biomedical Engineers. Proceedings of the 16th Annual International Conference of the IEEE, vol.2, pp. 1007 - 1008, 1994
[9] Mather, G.R., Jr., “Optical disc inspection by linear array CCD systems’’, Circuits and Systems, 1993., Proceedings of the 36th Midwest Symposium on, vol.2, pp. 1447 - 1455, 1993
[10] Zhang W.J., Li D., Ye F., Sun H., “Automatic Optical Defect Inspection and Dimension Measurement of Drill Bit”, Mechatronics and Automation, Proceedings of the 2006 IEEE International Conference on, pp.95 - 100, 2006
[11] Guifang Duan, Yen-Wei Chen, Sakekawa T., “Automatic Optical Inspection of Micro Drill Bit inPrinted Circuit Board Manufacturing Based onPattern Classification”, Instrumentation and Measurement Technology Conference Proceedings, 2008. IMTC 2008. IEEE , pp. 279 - 283, 2008
[12] Sassanapitak S., Kaewtrakulpong P., “An efficient translation-rotation template matching using pre-computed scores of rotated templates”, Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, 2009. ECTI-CON 2009. 6th International Conference on , vol. 02, pp.1040 - 1043, 2009
[13] Zheng Shuangyang, “Fast Inspection of Food Packing Seals Using Machine Vision ”, Digital Manufacturing and Automation (ICDMA), 2010 International Conference on , vol.1, pp. 724-726, 2010
[14] Morimoto M., Fujii K., “A visual inspection system for drug tablets ”, Systems, Man, and Cybernetics (SMC), 2011 IEEE International Conference on, pp.1106 - 1110, 2011
[15] Fupei Wu, Xianmin Zhang, Yongcong Kuan, Zhenzhen He, “ An AOI algorithm for PCB based on feature extraction” , Intelligent Control and Automation, 2008. WCICA 2008. 7th World Congress on , pp.240 - 247, 2008
[16] Fupei Wu, Xianmin Zhang,“Feature-Extraction-Based Inspection Algorithm for IC Solder Joints”, Components, Packaging and Manufacturing Technology, IEEE Transactions on , Issue.5 , vol.1, pp.689 - 694, 2011
[17] Shah Y.C., Chapman R., Mahani R.B., “A new technique to extract range information from stereo images” , Pattern Analysis and Machine Intelligence, IEEE Transactions on, Issue.7, vol.11 , pp. 768 - 773,1989
[18] Mengel P. “Automated inspection of solder joints on PC boards by supplementary processing of 3D and gray-level images”, Industrial Electronics Society, 1990. IECON '90., 16th Annual Conference of IEEE, vol.1 , pp.786 - 791, 1990
[19] Kong, Fan-Hui, “A New Method of Inspection Based on Shape from Shading”, Image and Signal Processing, 2008. CISP '08. Congress on, vol.2, pp.291 - 294, 2008
[20] de Meneses Y.L., Paratte J., Bhatia P., Kunzli S., “3DFlex: A flexible system for total visual inspection of bumped devices”, Electronic Manufacturing Technology Symposium (IEMT), 2010 34th IEEE/CPMT International, pp.1 - 4, 2010
[21] Tak-Wai Hui, Pang G.K.-H.,“3D Profile Reconstruction of Solder Paste Based on Phase Shift Profilometry”, Industrial Informatics, 2007 5th IEEE International Conference on, vol.1, pp.165 - 170, 2007
[22] Lavelle J.P., Schuet S.R., Schuet D.J., “High speed 3D scanner with real-time 3D processing”, Imaging Systems and Techniques, 2004. (IST). 2004 IEEE International Workshop on , pp.13 - 17, 2004
[23] Houkun Guo, Guoliang Xiong, Zhen Guo, Xiaohui Hu, “ Development on surface defect holes inspection based on image recognition”, Advanced Intelligent Mechatronics (AIM), 2010 IEEE/ASME International Conference on, pp.623 - 626, 2010
[24] Schaulin M., Wolter K.J., “White light interferometry, a method for optical 3D-inspection of advanced packages”, Electronics Technology: Meeting the Challenges of Electronics Technology Progress, 2004. 27th International Spring Seminar on, vol.1, pp. 42 - 46, 2004
[25] Schaulin, M., “White light interferometry for 3D inspection ”, Photonics and Microsystems, 2004. Proceedings of 2004 International Students and Young Scientists workshop , pp.41 - 45, 2004
[26] D. B. Perng, G. Y. Peng, C. J. Yan, and C. C. Chou, “A new machinevision system for SMD PCB auto-inspection”, The International Symposium on Measurement Technology & Intelligent Instrument ISMTII’ 2001, Cairo, Egypt, 25 - 29 Sept. 2001.
[27] 葉秋成, 王文豪,“影像處理與分析”, 碁峯資訊, 1995
[28] 劉震昌, “數位影像處理”, 高立圖書, 2010
[29] 台灣基恩斯股份有限公司：http://www.keyence.com.tw/
[30] 國立虎尾科技大學機械與機電工程學系機電光研究室。自動化光學檢測教材第一章概論。檢索日期：2012/5/1。檢自：http://140.130.15.147/%BE%F7%B9q%A5%FA%AC%E3%A8s%AB%C7/Course%20materials.htm
[31] 朱志良,林晉廷,劉丞哲“白光干涉儀”檢索日期：2012/5/1。檢自：eshare.stut.edu.tw/EshareFile/2010_12/2010_12_bcf96604.ppt