臺灣博碩士論文加值系統

近年由於影像辨識與工業自動化的迅速發展，全球正逐漸將生產自動化，人工檢驗也逐漸由自動化光學檢測技術(AOI)取代。現階段影像檢測技術正逐步導入到各項生產製造業上，而目前藥粒的檢測相關研究中，僅有部份資料顯示在大型藥粒有相關影像檢測研究。
因目前於包覆型藥粒的檢測研究上，尚無有相關自動檢測以及探討藥粒內部滲透之程度，因此本論文提出一個包覆型藥粒外型尺寸與藥劑滲透程度影像辨識檢測系統，其研究使用視覺光學檢測(AOI)與自動化技術，由藥粒專用研磨機台將藥粒研磨面處理平整，並對於具有藥劑滲透層的藥粒，顯現出藥劑滲透的研磨面，並由藥粒影像檢測軟體介面，以MODBUS與機台進行通訊，將固定於粹盤上的藥粒依序擷取圖像，透過影像辨識與量測，以HSV色彩空間抓出藥劑滲透層於藥粒的占有比例與孔洞內徑，影像邊緣算子抓取藥粒外徑，最後透過藥粒檢測軟體輔助介面協助數據分析，並將數據儲存於單機數據庫。本檢測系統在單次可檢測藥粒樣本至多為36顆，並由機台進行加工，其檢測的數據具依據性與一定標準，未來可透過大量檢測數據分析進而改善製程。

In recent years, due to the rapid development of image recognition and industrial automation, The world is developing production automation, Manual inspection is also gradually being replaced by automated optical inspection technology (AOI). At this stage, image detection technology is gradually introduced into various manufacturing industries, and in the research related to the detection of deterred grains, Only part of the data shows that there are related image detection studies in large-sized deterred grains.
At present, there is no relevant automatic detection and the degree of drug particles and internal penetration in the research of deterred grains. Therefore, this paper proposes an Image Recognition and Detection System for Dimensions and Deterrent Penetration of Deterred Grains, Visual Optical Inspection (AOI) and automation technology are used. The grinding surface of the grains is smoothed by a grain special grinding machine, and deterred grains with a grains penetration layer, the grinding surface of the grain penetration is displayed. The grains image detection software interface communicates with the machine through MODBUS, and the grains fixed on the tray are sequentially captured. Through image recognition and measurement, the proportion of the deterrent penetration layer in the grains and the inner diameter of the hole are captured in the HSV color space. The image edge operator captures the outer diameter of the medicine pellets, assists in data analysis through the medicine pellet detection software, and stores the data in a stand-alone database. This detection system can detect up to 36 deterred grains samples in once, and they are processed by a machine. The detected data is based and standard. In the future, a large amount of detection data can be analyzed to improve the manufacturing process.

摘　要 ii
Abstract iii
誌　謝 iv
目　錄 v
表　目　錄 vii
圖　目　錄 viii
第1章 緒論 1
1.1研究背景與研究動機 1
1.2 先前技術 3
1.3研究目的 6
1.4論文架構 7
第2章 藥粒檢測前置處理 8
2.1 粹盤藥粒研磨面處理 9
2.1.1粹盤藥粒群研磨加工 9
2.1.2藥粒圖像擷取 11
2.2 藥粒影像前處理 13
2.2.1 影像濾波(Image Filter) 13
2.2.2影像特徵提取(Feature extraction) 15
2.2.3 型態學應用(morphology) 19
第3章 藥粒影像檢測軟體開發 22
3.1藥粒影像辨識 23
3.1.1. 藥粒影像擷取 23
3.1.2. 藥粒輪廓擷取 24
3.1.3 藥劑滲透程度辨識與孔洞大小分析 26
3.2辨識軟體輔助介面開發 29
3.2.1.藥粒點距離與人工量測取樣 29
3.2.2. 藥粒輪廓層與藥劑滲透層校正分析 32
3.2.3 藥粒影像計算實際尺寸之方法 34
第4章 實驗結果與討論 36
4.1 實驗設備 36
4.1.1 藥粒專用研磨機台硬體設備 36
4.1.2. 影像光學硬體設備 37
4.2 軟體開發環境介紹 38
4.3影像檢測與人工檢測比較 39
4.4測試結果與討論 45
第5章 未來展望 46
參考文獻 47

[1] A. Grau, M. Indri, L. L. Bello and T. Sauter, "Industrial robotics in factory automation: From the early stage to the Internet of Things," IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society, Beijing, 2017, pp. 6159-6164, doi: 10.1109/IECON.2017.8217070.
[2] K. H. Tantawi, A. Sokolov and O. Tantawi, "Advances in Industrial Robotics: From Industry 3.0 Automation to Industry 4.0 Collaboration," 2019 4th Technology Innovation Management and Engineering Science International Conference (TIMES-iCON), Bangkok, Thailand, 2019, pp. 1-4, doi: 10.1109/TIMES-iCON47539.2019.9024658.
[3] H. Gruschinski, "The future of the industrial robotics market," 2015 IEEE 20th Conference on Emerging Technologies & Factory Automation (ETFA), Luxembourg, 2015, pp. 1-4, doi: 10.1109/ETFA.2015.7301627.
[4] 亞洲推動自動化,Retrieved from https://de.statista.com/infografik/9080/weltweiter-absatz-von-mehrzweck-industrierobotern/,IFR
[5] World Robotics 2019 Industrial Robots,IFR
[6] V. Chaudhary, I. R. Dave and K. P. Upla, "Automatic visual inspection of printed circuit board for defect detection and classification," 2017 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET), Chennai, 2017, pp. 732-737, doi: 10.1109/WiSPNET.2017.8299858.
[7] A. Sathe and A. Deshpande, "Automated visual quality inspection and sorting," 2017 International Conference on Advances in Computing, Communication and Control (ICAC3), Mumbai, 2017, pp. 1-6, doi: 10.1109/ICAC3.2017.8318768.
[8] A market overview of global and Chinese Automated Optical Inspection (AOI) Market, Retrieved from https://aoi-spi.com/automated-optical-inspection-market/
[9] C. Qiu, "Size measurement of shaft component based on computer vision," 2012 5th International Congress on Image and Signal Processing, Chongqing, 2012, pp. 216-219, doi: 10.1109/CISP.2012.6469848.
[10] A. Thamna, P. Srisungsitthisunti and S. Dechjarem, "Real-Time Visual Inspection and Rejection Machine for Bullet Production," 2018 2nd International Conference on Engineering Innovation (ICEI), Bangkok, 2018, pp. 13-17, doi: 10.1109/ICEI18.2018.8448641.
[11] KEYENCE,IM-7000系列影像量測儀, Retrieved from https://www.keyence.com.tw/products/measure-sys/
[12] COGNEX視覺檢測方案, Retrieved from https://www.cognex.com/zh-tw/applications/products-in-action/bottle-inspection
[13] Kar-Hsien Fang and C.-K., Yang, “Evaluation of the Determination Methods for Barium Nitrate in Propellant,” National Taipei University of Technology Institute of Chemical Engineering, pp.1-104, 2008.
[14] Andrzej MAJCHER, Jan PRZYBYLSKI, and Jarosław FIGARSKI, “A Control System for Stand for Measuring the Burn Rate of Solid Rocket Propellants Using Crawford’s Method,” Journal of Machine Construction and Maintenance, pp.67-73, 2017.
[15] “Military Standard Product Cleanliness Levels Contamination Control Program,”MIL-Sm-1246C, pp.1-36, 11 April 1994.
[16] Susan Taylor, Katerina Dontsova, Susan Bigl, Colleen Richardson, James Lever, Jonathan Pitt, John P. Bradley, Marianne Walsh, and Jiří Šimůnek, “Dissolution Rate of Propellant Energetics from Nitrocellulose Matrices,” US Army Corps of Engineers, Engineer Research and Development Center, ER-1691 ERDC/CRREL TR-12-9, (September 2012)
[17] WU CHUNG-WEN, 以爆彈儀探討藥粒成份與藥型對燃燒特性的影響,2001
[18] K. N. Hittanagi, M. Ramesh, K. N. R. Kumar and S. K. Mahadeva, "PLC based DC drive control using Modbus RTU communication for selected applications of sugar mill," 2017 International Conference on Circuits, Controls, and Communications (CCUBE), Bangalore, 2017, pp. 80-85, doi: 10.1109/CCUBE.2017.8394156.
[19] S. A. Idris, F. A. Jafar and S. Saffar, "Improving visual corrosion inspection accuracy with image enhancement filters," 2015 12th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI), Goyang, 2015, pp. 129-132, doi: 10.1109/URAI.2015.7358876.
[20] 高斯二維的空間分佈,Retrieved from
https://www.twblogs.net/a/5b7ca2122b71770a43dbe9c8
[21] N. Otsu, "A Threshold Selection Method from Gray-Level Histograms," in IEEE Transactions on Systems, Man, and Cybernetics, vol. 9, no. 1, pp. 62-66, Jan. 1979, doi: 10.1109/TSMC.1979.4310076.
[22] J. Canny, "A Computational Approach to Edge Detection," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-8, no. 6, pp. 679-698, Nov. 1986, doi: 10.1109/TPAMI.1986.4767851.
[23] H. S. Hashim, S. N. H. S. Abdullah and A. S. Prabuwono, "Automated visual inspection for metal parts based on morphology and fuzzy rules," 2010 International Conference on Computer Applications and Industrial Electronics, Kuala Lumpur, 2010, pp. 527-531, doi: 10.1109/ICCAIE.2010.5735137.
[24] Ming-Kuei Hu, "Visual pattern recognition by moment invariants," in IRE Transactions on Information Theory, vol. 8, no. 2, pp. 179-187, February 1962, doi: 10.1109/TIT.1962.1057692.
[25] Wang Kejia, Zhang Honggang, Chai Lunshao, Haiying and Z. Ping, "A comparative study of moment-based shape descriptors for product image retrieval," 2011 International Conference on Image Analysis and Signal Processing, Hubei, 2011, pp. 355-359, doi: 10.1109/IASP.2011.6109062.
[26] L. Feng, L. Xiaoyu and C. Yi, "An efficient detection method for rare colored capsule based on RGB and HSV color space," 2014 IEEE International Conference on Granular Computing (GrC), Noboribetsu, 2014, pp. 175-178, doi: 10.1109/GRC.2014.6982830.
[27] D. S. Y. Kartika and D. Herumurti, "Koi fish classification based on HSV color space," 2016 International Conference on Information & Communication Technology and Systems (ICTS), Surabaya, 2016, pp. 96-100, doi: 10.1109/ICTS.2016.7910280.