跳到主要內容

臺灣博碩士論文加值系統

(44.213.60.33) 您好!臺灣時間:2024/07/21 12:25
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:林庭鋒
研究生(外文):LIN, TING-FENG
論文名稱:基於霍夫轉換與產品規格之量化影像分析於自動化視覺檢測系統研究
論文名稱(外文):Research of Automatic Visual Inspection System Using Quantitative Image Analysis Based on Hough Transforms and Product Specifications
指導教授:張元翔張元翔引用關係
指導教授(外文):CHANG, YUAN-HSIANG
口試委員:鄭立德蘇志文
口試委員(外文):ZHENG, LI-DESU,ZHI-WEN
口試日期:2023-07-28
學位類別:碩士
校院名稱:中原大學
系所名稱:資訊工程學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2023
畢業學年度:111
語文別:中文
論文頁數:41
中文關鍵詞:自動化視覺檢測機器視覺邊緣檢測霍夫轉換
外文關鍵詞:Automatic Visual InspectionComputer VisionEdge DetectionHough Transform
DOI:10.6840/cycu202301394
相關次數:
  • 被引用被引用:0
  • 點閱點閱:82
  • 評分評分:
  • 下載下載:24
  • 收藏至我的研究室書目清單書目收藏:0
在工業4.0時代,自動化視覺檢測已成為確保產品品質、減輕勞動密集型和減少耗時的產品檢測過程的重要問題。在本研究中,我們提出了一種自動視覺檢測系統,用於量化分析產品,即帶有鑽孔的鋼板,以確定產品是否符合所需規格。方法包括:感興趣區域提取、參考點定位、使用霍夫轉換進行圓孔檢測、影像和世界座標轉換,以及使用產品規格進行量化量測和分析。在初步的案例研究中,我們的系統在鑽孔數量的檢測上能夠達到100%的準確率,而在鑽孔座標和半徑方面的平均量測誤差均不超過0.5mm。綜上所述,我們的自動視覺檢測系統可以應用於實際的製造過程中,從而減少人為干預和人力成本,確保產品品質。
In the era of Industry 4.0, automatic visual inspection has become an important issue to assure the quality of the products, while alleviating labor-intensive and time-consuming manufacturing processes. In this study, we present an automatic visual inspection system to quantitatively analyze products, i.e., steel plates with drilled holes, to determine if the products meet the desired specifications. The methods include: Reference Landmark Localization, Region of Interest Extraction, Circular Hole Detections using Hough Transform, Image & World Coordinates Transformation, and Quantitative Measurements and Analysis using Product Specifications, respectively. During the preliminary case studies, our system was able to achieve 100% accuracy of quantity detections (i.e., all drilled holes are detected) and reasonable accuracy with the average measurement errors within 0.5 mm in terms of positions and radii, respectively. In summary, our automatic visual inspection system can be incorporated during the manufacturing processes in real scenarios, thus leading to alleviate manual inspection and intervention and assure product quality.
目次
摘要…………………………………………………………………..….…...…..I
Abstract...……………………………………………………………..…………II
致謝……………………………………………………………………..……...III
目次……………………………………………………………………..……...IV
圖目錄…………………………………………………………………..……...VI
表目錄…………………………………………………………………..……..VII
第一章 緒論……………………………………………………………..……...1
研究背景…………………………………………………………...…..1
文獻回顧……….……………………………………...…………...…..2
研究動機及目的…………………………………………………...…..4
第二章 基礎理論…………………………………………………………...…..5
Canny Edge Detector………………………………………..………….5
Hough Transform…………………………...…………………………..7
第三章 研究方法…………………………………………..………………….11
拍攝檢測影像…………………………………………………………11
感興趣區域提取…………………………………………...…………14
參考點定位………………………………………………...…………15
使用霍夫轉換進行圓孔檢測……………………………...…………19
影像和世界座標轉換……………………………...…………………24
使用產品規格進行定量量測和分析……………………...…………25
第四章 研究結果……………………………………………..……………….27
研究設備與環境…………………………………...…………………27
研究結果……………………………………………………...………28
第五章 結論與未來展望…………………………………………………..….33
參考文獻………………………………………………………..……………...34















圖目錄
圖2.1 霍夫域中直線上一點…………………………………………………...7
圖2.2 影像空間(x,y),參數空間(ρ,θ)………………….…………..………….8
圖2.3 基於梯度的霍夫圓檢測法示意圖…………………….……….………..9
圖3.1 機構設計圖…………………………………………….…………..…...11
圖3.2 拍攝流程示意圖……………………………………….…………..…...12
圖3.3 用於自動視覺檢測系統的影像……………………….……..………...13
圖3.4 本文提出的自動視覺檢測系統之軟體流程圖……….……..………...14
圖3.5 感興趣區域提取示意圖……………………………….……..………...15
圖3.6 找對應圓演算法流程圖……………………………….……..………...17
圖3.7 參考點定位結果……………………………………….……..………...17
圖3.8 旋轉角度示意圖……………………………………….……..………...18
圖3.9 第一次圓孔檢測流程圖……………………………….……..………...20
圖3.10 處理後的ROI影像及檢測結果……………………….……..……….21
圖3.11 第二次圓孔檢測流程圖……………………………….………..…….22
圖3.12 處理後的ROI影像與檢測結果……………………….………..…….23
圖3.13 檢測到的圓孔示意圖………………………………….………..….....23
圖3.14 使用產品規格進行定量量測和分析示意圖………….………..….....26
圖4.1 縮放比例高斯分布圖…………………………………….………..…...28
圖4.2 檢測座標偏移影像……………………………………….………..…...32
表目錄
表2.1 Canny函式的參數解釋………………….………………………..……...6
表2.2 HoughCircles函式的參數解釋………….…………………………..….10
表4.1系統研究之硬體設備.……………………………………………..…....27
表4.2 圓孔數量檢測結果……………………….………………………..…...30
表4.3 圓孔座標檢測結果……………………….………………………..…...30
表4.4使用產品規格進行的定量量測和分析結果.……………………..…....31
表4.5 本自動化視覺檢查系統之誤判率……….………………………..…...31

[1]M. J. Aschwanden, “Image processing techniques and feature recognition in solar physics,” Solar Physics, vol.262, no.2, pp.235-275, 2010.
[2]N. Thakur, “Feature extraction: an application to object and image recognition,” International Journal of Latest Trends in Engineering and Technology, vol.9, no.1, pp.178-184, 2017.
[3]A. Tiwari, “Feature Extraction for Object Recognition and Image Classification,” International Journal of Engineering Research & Technology (IJERT), vol.2, no.10, pp.1238-1246, 2013.
[4]H. Rau, and C.-H. Wu, “Automatic optical inspection for detecting defects on printed circuit board inner layers,” International Journal of Advanced Manufacturing Technology, vol.25, no.9-10, pp.940–946, 2005.
[5]S. Abdelhedi, K. Taouil, and B. Hadjkacem, “Design of automatic vision-based inspection system for monitoring in an olive oil bottling line,” International Journal of Computer Applications, vol.51, no.21, pp.39–46,2012.
[6]Y.-C. Wang, J.-C. Lin, and S.-F. Chiu, “The automatic image inspection system for measuring dimensional parameters of a saw blade,” Proc. of the 8th IEEE Int. Conf. on Control and Automation (ICCA), pp.1557-1561, 2010.
[7] J. Canny, “A Computational Approach to Edge Detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-8, no.6 pp.679-698, 1986.
[8]P. V. C. Hough, “Method and means for recognizing complex patterns,” US Patents 3069654A [P], 1962-12-18.
[9]R. O. Duda, P. E. Hart, “Use of the Hough transformation to detect lines and curves in pictures,” Communications of the ACM, vol.15, no.1, 1972.
[10] D.-H. Ballard, “Generalizing the Hough transform to detect arbitrary shapes,” Pattern Recognition, vol.13, no.2, pp.111-122, 1981.
[11] A.-O. Djekoune, K. Messaoudib, and K. Amaraa, “Incremental circle Hough transform: An improved method for circle detection,” Optik, vol.133, pp.17-31, 2017.
[12] A. Manzanera, T.-P. Nguyen, and X.-L. Xu, “Line and circle detection using dense one-to-one Hough transforms on greyscale images,” Eurasip Journal on Image and Video Processing, vol.2016, no.1, pp.1-18, 2016.
[13] P. Mukhopadhyay, and B. B. Chaudhuri, “A survey of Hough transform,” Pattern Recognition, vol.48, no.3, pp.993–1010, 2015.
[14] J. Illingworth, and J. Kittler, “The Adaptive Hough Transform,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.PAMI-9, no.5, pp.690-698, 1987.

QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊