Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/89992
標題: A Study on the Detection for the Oil Seals with Machine Vision
應用機器視覺於油封環檢測之研究
作者: Tzu-Yan Xu
徐子晏
關鍵字: 機器視覺
油封環
法線向量
檢測線
machine vision
oil-seal
normal vector
detection line
引用: [1] 財政部關務署-海關統計。 https://portal.sw.nat.gov.tw/APGA/GA01 [2] 嵩贊油封工業股份有限公司。 http://wenku.baidu.com/view/c4876f781711cc7931b71697 [3] 范光照,廖偉博。環形粉末冶金件之自動光學檢測。粉末冶金會刊第 33卷第3期。2008年 [4] 謝正豪。2013。應用機器視覺於隱型眼鏡瑕疵檢測之研究。碩士論文。華梵大學機電工程學系 [5] L. Angrisani, P. Dapont, A. Pietrosant, C. Liguor, 'An image-based measurement system for the characterisation of automotive gaskets,' Measurement 1999, 25(3), 169-181. [6] D. M. Tsai, 'A Machine Vision Approach for Detecting and Inspecting Circular Parts,' The International Journal of Advanced Manufacturing Technology, 1999, 15, 217-221. [7] L. Jiang, X. Zhang, 'Inspection algorithm based on Gaussian filtering for oil seal spring,' SPIE.Digital Library, 2014, Opt. Eng. 53(10). [8] M. Zhang, H. Cao, 'A New Method of Circle's Center and Radius Detection in Image Processing,'IEEE Transactions on Automation and Logistics Qingdao,China, 2008, 9, 2239-2242. [9] F. Adamo, F. Attivissimo, A. D. Nisio, M. Savino, 'A low-cost inspection system for online defects assessment in satin glass,' Measurement, 2009, 42(9), 1304-1311. [10] F. Duan, Y. N. Wang, H.J. Liu, Y. G. Li, 'A machine vision inspector for beer bottle,' Engineering Applications of Artificial Intelligence 2007, 20(7), 1013-1021. [11] S. S. Martinez, J. G. Ortega, J. G. Garcia, A. S. Garcia, 'A machine vision system for defect characterization on transparent parts with non-plane surfaces', Machine Vision and Applications, 2012, 23, 1-13. [12] T. H. Sun, F. C. Tien, F. C. Tien, R. J. Kuo, 'Automated Thermal Fuse Inspection Using Machine Vision and Artificial Neural Networks', J Intell Manuf, 2014, March. [13] N. Otsu. 'A Threshold Selection Method from Gray-Level Histograms' IEEE Transactions on Systems, Man and Cybernetics 1979, 9(1), 62-66. [14] R.C.Gonzalez, R.E. Woods (2008), 'Digital Image Processing Third Edition' Prentice Hall. [15] I. Sobel, 'Neighborhood Coding Of Binary Images For Fast Contour Following And General binary array processing' Computer Graphics And ImageProcessing 1978, 8, 127-137. [16] R. Osserman, 'The isoperimetric inequality,' Bull. Am. Math. Soc, 1978, 84, 1182-1238.
摘要: 本研究之目的在於建立一套以法線向量為檢測線,結合影像處理技術之油封環檢測系統。本研究使用的影像處理技術包含二值化、補洞運算、邏輯運算、邊界鏈碼、輪廓追蹤法與法線向量檢測線,針對油封環的外徑、內徑、線徑、最大與最小線徑進行計算,並檢測瑕疵(內外毛邊或內外缺口)是否存在。 本研究建立的法線向量量測法則,針對油封環局部輪廓之局部輪廓,分別以向量均值法與三角端點法定義法線向量進行檢測,並比較其差異。進一步再以均值等分的方式進行法線向量的校正,並進行線徑的量測、瑕疵的檢測。可達到線上即時檢測的功能,同時解決油封環在運動過程中因變形而造成量測誤差的問題。 本研究利用提出的法線向量量測法則針對不易變形的油封環(T01290)與易變形的油封環(T02346)進行量測,由結果顯示,使用向量均值法與三角端點法針對860張不易變形油封環的準確率分別為97.44%與97.09%、129張易變形油封環分別為88.37%與89.14%,由以上結果得知,本研究提出的量測法則可有效地量測不同形態的油封環。
In this study, the measurement system for the oil seals is developed with machine vision. Image processing techniques including binary, hold-filling operation, logical operation, edge linkage, edge following, detection line and the normal vector algorithm are used to detect outside diameter, inside diameter, wire and defects for oil seals. The mean and triangle methods after equisection calibration are compared for detecting the profile of oil seal. The accuracies of detection were 94.77% and 94.53% for normal oil seals (860 samples), 88.37% and 89.14% for distortion oil seals (129 samples) using the mean and triangle methods, respectively. Testing results showed that the oil seals can be detected and classified efficiently using the developed system.
URI: http://hdl.handle.net/11455/89992
其他識別: U0005-2401201518582900
文章公開時間: 2017-02-04
Appears in Collections:生物產業機電工程學系

文件中的檔案:

取得全文請前往華藝線上圖書館

Show full item record
 
 
Citations:


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.