臺灣博碩士論文加值系統

機器視覺系統主要是在影像上進行特徵點偵測，並透過這些特徵點進行分析與應用，如尺寸檢測、瑕疵檢測、精密定位等。而本研究以機器視覺為基礎開發一套特徵重建演算法，透過CCD元件擷取物件影像，經過小波去噪以及解析度調整，搭配SLIC超像素分割法將影像內的各封閉曲線分離出來。接著使用形態學處理取得物體的外型輪廓，並提出一種以向量循邊為基礎的特徵點偵測法來進行特徵點辨識，利用特徵點分割物體外型輪廓，將輪廓進行線段分類與重建，使我們獲得物體的尺寸資訊及輪廓特徵資訊，希望能讓使用者藉由這些數據，進行工具機加工數據回饋及統計分析。在後續也針對不同情況下的特徵點辨識能力作探討，與一般常用角點偵測算子做比較，在不同影像解析度與旋轉角度下，本研究所開發之特徵點偵測法依然可正確的完成偵測。而我們也取三種不同複雜度外型的物件來進行辨識與重建，皆能達到正確的重建結果。

The machine vision system focuses on detecting feature points on the image as well as analyzing these feature points for various applications such as size detection, defect detection, precision positioning, and so on. The main purpose of this paper is to develop a feature reconstruction algorithm based on machine vision. First of all, we capture the object image by CCD component, undergoing the process of wavelet denoising and resolution adjustment. Via SLIC super-pixel segmentation, we separate the closed curves in the image, and then obtain the contour of the separated objects by means of morphological processing. In this study, we propose a feature point detection method based on vector edge tracing. The contours of our concerned objects are segmented via feature points. Then these contours are categorized and reconstructed so as to obtain the size and contours information. We hope users can utilize these data in machining data feedback and statistical analysis. Next, we discuss the feature point detection ability for our method under different circumstances. In comparison to commonly used corner detection operator, our method can still correctly complete the identification under different image resolutions and rotation angles. Besides, we take three objects with different complexities to identify and reconstruct via our methods. All the results are correctly reconstructed.

誌謝 I
摘要 II
ABSTRACT III
目錄 IV
圖目錄 VII
表目錄 XI
第一章 緒論 1
1.1 研究背景 1
1.2 文獻回顧 1
1.2.1 特徵群分類法回顧 2
1.2.2 特徵點辨識演算法回顧 2
1.3 研究動機與目的 3
1.4 論文大綱 4
第二章 相關技術理論 5
2.1 圖像分割 5
2.1.1 圖像分割原理 5
2.1.2 SLIC超像素圖像分割 7
2.2 邊緣偵測 10
2.2.1 邊緣偵測基本原理 10
2.2.2 邊緣偵測運算子 10
2.3 二值化處理 11
2.4 角點偵測 14
2.5 雜訊抑制 20
2.5.1 雜訊種類 20
2.5.2 以小波分析抑制雜訊 22
2.6 形態學處理 28
第三章 演算法設計流程 30
3.1 實驗設備 31
3.2 影像預處理 32
3.3 影像分割 45
3.4 特徵點偵測 48
3.4.1 邊緣偵測及平滑化 49
3.4.2 像素點排序 53
3.4.3 特徵點辨識 54
3.4.4 特徵點修正 57
3.5 特徵類型辨識與重建 60
3.5.1 線段辨識 60
3.5.2 特徵重建 65
第四章 實驗結果與討論 75
4.1 尺度不變性及旋轉不變性測試 75
4.2 曲線段曲率變化分析 89
4.3 不同幾何圖形之重建結果 93
4.3.1 拍攝角度校正 93
4.3.2 樣本一之重建結果 95
4.3.3 樣本二之重建結果 97
4.3.4 樣本三之重建結果 99
4.3.5 重建結果之探討 101
4.4 自動辨識流程之建立 105
第五章 結論與未來展望 111
5.1 結論 111
5.2 未來展望 112
參考文獻 113

[1]C.Bradley, G.W.Vickers, and M.Milroy, “Reverse engineering of quadric surfaces employing three-dimensional laser scanning.” Proceedings of the Institution of Mechanical Engineers, Part B, Journal of Engineering Manufacture 208.1, pp.21–28,1994
[2]O.Bartholomew. Nnaji, Tzong‐Shyan Kang, Shuchieh Yeh, Jang‐Ping Chen,“Feature Reasoning for Sheet Metal Components”, International Journal of Production Research, pp.1868–1896,1991
[3]J.Besl,Paul, C. Jain ,Ramesh, “Invariant surface characteristics for 3D object recognition in range images.” Computer vision, graphics, and image processing 33.1, pp.33–80,1986
[4]Chris Harris & Mike Stephens,” A COMBINED CORNER AND EDGE DETECTOR”, Proceedings of 4th Alvey Vision Conference, pp.189-192,1988
[5]Moravec, P.Hans.,” towards automatic visual obstacle avoidance.”, IJCAI''77 Proceedings of the 5th international joint conference on Artificial intelligence - Volume 2 ,pp.584-584
[6]Rabih Al Nachar and Elie Inaty,” A Robust Edge Based Corner Detector”, 17th IEEE Mediterranean Electrotechnical Conference, Beirut, Lebanon, 13-16 ,April 2014.
[7]Xiao Chen He, Nelson H.C.Yung,” Corner detector based on global and local curvature properties”, Optical Engineering 47(5), May 2008
[8]Edward Rosten and Tom Drummond,” Fusing Points and Lines for High Performance Tracking”, International Conference on Computer Vision (ICCV’05),2005
[9]Radhakrishna Achanta, Appu Shaji, Kevin Smith,Aurelien Lucchi, Pascal Fua, and Sabine S¨usstrunk,” SLIC Superpixels Compared to State-of-the-art Superpixel Methods”, Journal of latex class files, vol.6, no.1, December 2011
[10]Xiu-yong Wu, Ke Xu and Jin-wu Xu,”Application of Undecimated Wavelet Transform to surface defect detection of hot rolled steel plates”, Image and Signal Processing, 2008.
[11] Jianbo Shi and Carlo Tomasi,“Good Features to Track”,IEEE Conference on Computer Vision and Pattern Recognition(CVPR94) Seattle,June 1994
[12] L. Debnath, “Wavelet Transforms and Their Application”,Birkhauser, Boston,USA, 2002.
[13] C. Rother, V. Kolmogorov, and A. Blake, “Interactive foreground extraction using iterated graph cuts”, ACM Trans. Graph., vol. 23, pp.309–314, 2004
[14] Du-Ming Tsai, Bo Hsiao,” Automatic surface inspection using wavelet reconstruction”, Pattern Recognition 34 ,pp.1285-1305,2001
[15] T.Aarthi, M.Karthi, M.Abinesh,”Detection and Analysis of Surface Detects in Metal Using Wavelet Transform”, International Journal of Scientific and Research Publications, Volume 3, Issue 6, June 2013
[16] L. Grady,”Random Walks for Image Segmentation”, IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 28, No. 11, pp.1768–1783, Nov., 2006.
[17] S. Johnson,”Stephen Johnson on Digital Photography”, O''Reilly,2006
[18] LS. Davis, "A survey of edge detection techniques", Computer Graphics and Image Processing, vol 4, no. 3, pp 248-260, 1975
[19] Gonzalez and R. Woods,” Digital Image Processing”, Addison Wesley,
pp.414-428,1992
[20] F.Meyer and S.Beucher, “Morphological segmentation”, J.Vis.Commun.Image Represent., Vol.1, pp.21-46, Sept.1990.
[21] Nobuyuki Otsu,” A Tlreshold Selection Method from Gray-Level Histograms”, IEEE Transactions on Systems, man, and cybernetics, vol.smc-9, no.1, January 1979
[22] D.L.Donoho, "De-noising by soft-thresholding," IEEE Trans. on Inf. Theory, 41, 3, pp. 613–627,1995
[23]A.N. Akansu, R.A. Haddad and H. Caglar, “Perfect Reconstruction Binomial QMF-Wavelet Transform”, SPIE Visual Communications and Image Processing, pp. 609–618, Sept. 1990
[24] S. Grace Chang, Bin Yu, and Martin Vetterli,”Adaptive Wavelet Thresholding for Image Denoising and Compression”,IEEE Transactions On Image Processing, Vol. 9, No. 9, Sept .2000
[25] 唐向宏,李齊良,”時頻分析與小波變換”,科學出版社,2008
[26] S.Mallat, WL.Hwang. “Singularity Detection and Processing with Wavelets” ,IEEE transactions on information theory, vol. 38, no. 2, March 1992.
[27] A. Boggess, F.J. Narcowich ,”A first course in Wavelets with Fourier Analysis”, John Wiley & Sons ,2001
[28] M.Abo-Zahhad, Sabah M. Ahmed, and Ahmed Zakaria, “An Efficient Technique for Compressing ECG Signals Using QRS Detection Estimation and 2-D DWT Coefficients Thresholding”, Modelling and Simulation in Engineering Volume 2012, October 2012
[29] Jules R. Dim, Tamio.Takamura "Alternative Approach for Satellite Cloud Classification: Edge Gradient Application",Advances in Meteorology. 2013
[30] L.Evans, “Partial Differential Equations”, American Mathematical Society,1998
[31] J.Canny, “A Computational Approach To Edge Detection”, IEEE Trans. Pattern Analysis and Machine Intelligence, 8(6),pp.679–698, 1986.
[32] D.C .Munson, ”A Note on Lena”,IEEE Transactions on Image Processing (Archive) 5 (1),January 1996