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：	黃志榮 Huang, Zhi-Rong
論文名稱：	自動檢測系統之定位、量測與辨識之研究 A Study on Orientation, Measurement and Recognition of an Automatic Inspection System
指導教授：	陳進興 Chen, Chin-Hsing
學位類別：	碩士 Master
系所名稱：	電機資訊學院 - 電機工程學系 Department of Electrical Engineering
論文出版年：	2003
畢業學年度：	91
語文別：	英文
論文頁數：	95
中文關鍵詞：	快速傅利葉轉換、迴歸分析、影像處理
外文關鍵詞：	FFT, Regression Analysis, Image Processing
相關次數：	點閱：87 下載：7
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

傳統檢測依靠人工，但是，人眼檢測缺乏效率且不可靠，因此，自動化檢測目前在工業中已是一種趨勢且被寬泛地利用。本篇論文研究三個關於自動化檢測系統的主題，分別為BGA晶片的分類、IC膠體的校準與積層陶瓷電容(MLCC)的量測。

對BGA晶片的分類，本論文分別利用區塊分析以及萃取骨架方法。在IC膠體的校準中，則分別使用區塊分析以及霍夫轉換來判斷方向。利用線性迴歸分析以及一維的區塊聚合法來找到IC膠體的中央位置和角度。在量測MLCC電容層寬的偏移量中，本論文先使用二次迴歸分析得到準線。利用快速傅利葉轉換得到電容層數，再使用校正特徵點演算法找出最準確的端點位置。最後，由端點位置和準線得到偏移量。

本論文的實驗使用了2種BGA產品共102個影像進行分類，結果顯示我們的方法皆可正確分類出合格與不合格的產品。平均花費時間上，區塊分析法需 20 ms，萃取骨架法則需225 ms。平均影像大小為226*268。另外，對IC產品共76個影像進行校準，結果顯示水平位置誤差的方均根值為0.316 pixel(s)，垂直位置為0.459 pixel(s)，角度為0.121' ，平均需時為 81 ms，平均影像大小為628*337。在判斷方向上，區塊方析的準確率為93.4%，平均需時5 ms，霍夫轉換的準確率為97.4%，平均需時310 ms。最後，對2種MLCC的產品共8個影像進行量測，結果顯示平均偏移量為3.19 pixel(s)，端點位置的平均誤差為1.433 pixel(s)，平均需時883.5 ms，平均影像大小為768*576。

Traditional inspection is manual, unreliable and inefficient. Therefore, automatic inspection would have great benefits and have been widely adopted for various automatic visual inspections in today’s industry. This thesis investigates three major issues concerning an automatic inspection system: the classification of BGA chips, the alignment of IC packages and the measurement of MLCC.

In classifying the BGA chip, the blob analysis method and the skeleton extraction method were used. In aligning the IC package, the blob analysis method and the Hough transform method were used for direction determination respectively. Linear regression analysis and region growing were used to find the center position and angle of an IC package. In measuring deviations of layer widths of the MLCC, 2nd order regression analysis was applied to obtain the datum curve. Fast Fourier transform was used to find the number of layers. Feature point alignment was used to align the edge points to the best positions. Finally, deviations from the datum curve to the positions of edge points were calculated.

In the experiments, two BGA products with total 102 images were used for classification. According to the results, all 102 images were correctly classified. 20 ms and 225 ms in average are required by blob analysis and skeleton extraction respectively and the average of image size is 226*228. An IC product with total 76 images were used for alignment. According to the results, the RMS errors of the horizontal and vertical positions are 0.316 and 0.459 pixel(s) respectively and the angle is 0.121' . 81 ms in average is required and the average image size is 628*337. As for direction determination, the correct rate is 93.4% and 5 ms in average is required in the blob analysis method, and the correct rate is 97.4% and 310 ms in average is required by the Hough transform method. Two MLCC products with total 8 images were used for measurement. According to the results, the average deviation is 3.19 pixel(s) and the average error of edge point position is 1.433 pixel(s). 883.5 ms in average is required and the average image size is 768*576.

              Contents

	Abstract	I
	Contents	III
	Figure Captions	VII
	Table Captions	XII
	Chapter 1 Introduction	1
1 Motivation	1
2 System Configuration	1
3 Types of Test Images	3
4 Organization of the Thesis	4
	Chapter 2 Image Pre-processing	5
1 Introduction	5
2 Histogram Techniques	5
2.1 Gray-Level Histogram	6
2.2 Histogram Equalization	7
3 Automatic Thresholding Methods	8
3.1 Definition	10
3.2 Otsu Method	10
3.3 Moment Preserving Method	12
4 Morphological Image Processing	16
4.1 Hit-or-Miss Transform	16
        2.4.2 Thinning and Thickening	18
4.2.1 Thinning	18
4.2.2 Thickening	19
5 Spatial Filters	20
5.1 Median Filter	21
5.2 Edge Detection	22
  Chapter 3 Classification of BGA Chips	25
1 Introduction	25
2 Definitions of “Good” and “Bad” BGA chips	27
3 Blob Analysis	27
3.1 Region Growing	28
3.2 Blob’s Characteristics	29
4 Skeleton Extraction	30
5 Experimental Results and Discussions	33
5.1 Experimental Results	33
5.2 Discussions	35
Chapter 4 Alignment of IC packages	36
1 Introduction	36
2 Image Segmentation	37
3 Direction Determination	39
3.1 Hough Transform Method	42
3.2 Blob Analysis Method	45
4 Line Fitting and Angle Calculation	47
4.1 Selecting the Data Points for Fitting	48
        4.4.2 Linear Regression Analysis	49
4.3 Angle Calculation	51
5 Calculation of the Center Position	53
6 Experimental Results and Discussions	55
6.1 Experimental Results	55
6.2 Discussions	57
	Chapter 5 Measurement of MLCC	58
1 Introduction	58
2 Image Segmentation	61
3 Curve Fitting	65
3.1 Selecting the Data Points for Fitting	65
3.2 2nd Order Regression Analysis	66
4 Calculation of Layer Numbers	67
4.1 Fourier Analysis	68
4.1.1 Fourier Transform and Discrete Fourier 
	Transform	69
4.1.2 Fast Fourier Transform	71
4.2 Spectrum Analysis	72
4.3 Calculate the Number of Layers	75
5 Feature Point Alignment and Deviation Calculation	75
5.1 Global Feature Detection	77
5.2 Global Refinement	78
5.3 Local Matching	79
5.4 Deviation Calculation	80
6 Experimental Results and Discussions	81
6.1 Experimental Results	81
6.2 Discussions	83
	Chapter 6 Conclusions	84
1 Conclusions	84
2 Discussions	85
3 Future Directions	86
	Appendix I	87
	Appendix II	89
	References	93

                                    

[1] J. Canny, “A Computational Approach to Edge Detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 8, No. 6, pp. 679-697, November 1986.
[2] E. R. Dougherty, An Introduction to Morphological Image Processing, SPIE, 1992.
[3] C. R. Giardina and E. R. Dougherty, Morphological Methods in Image and Signal Processing, Prentice-Hall International, NJ, 1987.
[4] R. C. Gonzalez and R. E. Woods, Digital Image Processing, Prentice-Hall International, NJ, 2002.
[5] Hough, P.V.C. “Methods and Means for Recognizing Complex Patterns,” U.S. Patent 3069654, 1962.
[6] L. C. Hamilton, Regression with Graphics, Wadsworth, Inc., 1992.
[7] A. K. Jain, S. Prabhakar, and L. Hong, “A Multichannel Approach to Fingerprint Classification,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 21, No. 4, pp. 348-359, April 1999.
[8] A. A. Kassim, H. Zhou, and S. Ranganath, “Automatic IC Orientation Checks,” Machine Vision and Applications, Vol.12, pp. 107-112, 2000.
[9] R. Li, B. Aeng and M. L. Liou, “A New Tree-Step Search Algorithm for Block Motion Estimation,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 4, pp. 438-442, August 1994.
[10] D. C. Montgomery and E. A. Peck, Introduction to Linear Regression Analysis, Wiley-Interscience, 1992.
[11] A. V. Oppenheim, A. S. Willsky, and S. H. Nawab, Signals and Systems, Prentice-Hall International, NJ, 1997.
[12] A. V. Oppenheim and R. W. Schafer, Discrete-Time Signal Processing, Prentice-Hall International, NJ, 1999.
[13] N. Otsu, “A Threshold Selection Method from Gray-Level Histograms,” IEEE Transactions on Systems, Man, and Cybernetics, SMC-9, pp. 62-66, 1979.
[14] I. Pitas, Digital Image Processing Algorithms, Prentice-Hall International, NJ, 1993.
[15] M. Sonka, V. Hlavac, and R. Boyle, Image Processing, Analysis, and Machine Vision, P.W.S, 1998.
[16] W. H. Tsai, “Moment-Preserving Thresholding: a New Approach,” Computer Vision, Graphics and Image Processing, Vol. 29, pp. 377-393, 1985.
[17] G. T. Uber, “Illumination Methods for Machine Vision,” Proceedings of SPIE, pp. 93-102, 1986.
[18] I. Weiss, “Line Fitting in a Noise Image,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 11, No. 3, pp. 325-329, March 1989.
[19] 吳正毅, “BGA 晶片印刷圖案自動化檢測之研究,” 碩士論文, 國立成功大學電機工程研究所, 2001.
[20] 邱振洋, “應用電腦視覺於IC 瑕疵檢測之研究,” 碩士論文, 國立雲林科技大學工業工程與管理研究所, 2000.
[21] 張綜麟, “積層陶瓷電容影像自動辨識之研究,” 碩士論文,國立成功大學電機工程研究所, 2002.
[22] 戴顯權, 資料壓縮, 紳藍出版社, 2001.

校內：立即公開
校外：2003-07-18公開

簡易檢索 / 詳目顯示

相關論文