成功大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	歐陽衡 OuYang, Heng
論文名稱：	機器視覺用在封裝IC外觀瑕疵檢測之研究 Application of Machine Vision for Packaged IC Surface defect detection
指導教授：	王明習 Wang, Ming-Shi
學位類別：	碩士 Master
系所名稱：	工學院 - 工程科學系碩士在職專班 Department of Engineering Science (on the job class)
論文出版年：	2007
畢業學年度：	95
語文別：	中文
論文頁數：	54
中文關鍵詞：	封裝IC外觀檢測、檢測技術、電腦視覺
外文關鍵詞：	Inspection technology, Packaged IC Appearance Inspection, Computer Vision
相關次數：	點閱：82 下載：14
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

機器視覺(Machine Vision)檢測技術已廣泛地被應用在製造工業之生產製造、製程監控和品質管控。機器視覺系統之組成通常包括攝影機、光源、影像擷取卡、影像處理軟體及電腦等設備。本研究的目的是利用機器視覺來對封裝積體電路(IC)之外接引腳和膠體外觀分析，以判斷該封裝IC之外觀形狀是否符合規範。首先，由機器所取得之影像中切割出要受檢測之區域(Region Of Interest, ROI)，接著經過相關之影像處理後，利用與標準規範之形狀比對以決定受測對象是否符合最小規範所要求。本研究中共測試由生產線現場上所取得的152張影像，可正確檢出之比率達98.68%。

Machine Vision system has been widely used in manufacturing industry for production manufactures, production monitoring and quality control. Usually, a computer vision system includes camera, lighting, image capture card, required image processing software, and computer system. The purpose of this research is to use computer vision to do the appearance inspection of packaged IC. The subjects to be inspected are the pins layout and the packaged plastic appearance of the IC. Firstly, the regions of interest are isolated from the image which captured by the vision system set up on the delivery line of the factory. After properly image processing for the extracted image, the processed subject is compared with the standard sample to make a decision if it is satisfied the required specification. 152 testing images which captured on line were processed by the proposed approach. It is shown that the correct rate is 98.68%.

中文摘要...............................................................i
Abstract...............................................................ii
致謝.................................................................iii
目錄..................................................................iv
表目錄................................................................vi
圖目錄...............................................................vii
第一章	緒論...........................................................1
1.1	封裝製程概述...................................................1
1.2	研究動機、目的與重要性..........................................4
1.3	研究方法概述...................................................5
1.4	本文大綱.......................................................6
第二章	相關研究與影像處理方法.........................................7
2.1 過去的相關研究.................................................7
2.2 視覺系統架構組成要素...........................................8
2.3 影像處理的應用.................................................8
2.4 影像資料與前處理方法...........................................9
	2.4.1 影像資料.................................................9
    2.4.2 缺陷影像與種類..........................................10
	2.4.3 影像分割................................................12
	2.4.4 特徵點擷取..............................................14
	2.4.5 正規化相關匹配法(Normalized Cross Correlation, NCC).........17
	2.4.6 邊緣強化處理............................................19
	2.4.7 閥值(Threshold)與二值化處理..............................25
	2.4.8 外引腳的判斷............................................28
第三章	檢測系統架構..................................................30
3.1 檢測環境......................................................30
3.2 影像資料收集與統計............................................31
3.3 研究流程架構..................................................34
第四章	實驗結果與分析................................................37
4.1 統計實驗結果..................................................37
	4.1.1 外引腳影像資料統計結果..................................37
	4.1.2 執行時期之外引腳數量與統計值之比較......................40
4.2 執行時期影像檔案與影像前處理之正確性..........................41
	4.2.1 執行時期之影像檔案......................................41
	4.2.2 執行時期影像之正確性....................................45
4.3 膠體內影像測試結果............................................46
4.4 綜合影像測試結果..............................................48
第五章	結論與未來展望................................................50
5.1 結論..........................................................50
5.2 未來展望......................................................51
參考文獻..............................................................52
自述..................................................................54
                                    

[1] http://plastic.me.ntu.edu.tw/STUDY/study_multi.htm
[2] J.N.Kapur, P.K. Sahoo, and A.K.C. Wong, “A new method for gray-level picture thresholding using the entropy of the histogram,” Computer Vision, Graphics, andImage Processing, Vol. 29, pp.273-285. , 1985
[3] N. Otsu, “A threshold selection method from gray-level histogram”, IEEE Trans on Trans. Systems, Man and Cybernetics, Vol.9, pp62~66., 1979
[4] Rafel C. Gonzalez, Richard E. Woods, “Digital Image Processing 2/e”, Vol. 3, No. 4, 2003
[5] T. Sumimoto, T. Maruyama, Y. Azuma,S. Goto, M. Mondou, N. Furukawa, and S. Okada , ”Development of image analysis for detection of defects of BGA by using x-ray images,” IEEE Instrumenation and Measurement Technology Conference, VAIL, CO, USA, Vol. 2, pp.1131~1136, May, 2003
[6] Y. Hara ,N. Akiyamai,and K. Karasaki, ”Automation inspection for printed circuit board,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol.10, pp.69–78., 1988
[7] 饒忻, 曾健維, 許世麟, “自動化IC所字瑕疵檢測(II)-瑕疵辨識”, Journal of the Chinese Institute of Industrial Engineers, Vol. 20, No. 4, pp327-336, 2003
[8] 鍾國亮, “影像處理與電腦視覺”, 第三版, 東華書局, 2006
[9] 邱顯達, “自動化IC檢視與辨認系統之研究”, 國立成功大學機械工程研究所碩士論文, 1994
[10] 鄭睿夫, “影像處理技術於載帶規範檢測之應用“, 國立成功大學工程科學所碩士論文, 2001
[11] 張育賢, “利用影像區域特性於晶圓表面瑕疵自動化檢驗”, 國立清華大學工業工程研究所碩士論文, 1995
[12] 唐為璽, “沖壓件高速檢驗系統--以晶片接腳檢驗為例”, 國立清華大學工業工程研究所碩士論文, 1994
[13] 張維娜, “BGA基板視覺檢測”, 國立交通大學, 電機與控制工程系所碩士論文, 2003

校內：立即公開
校外：2007-08-20公開

簡易檢索 / 詳目顯示

相關論文