臺灣博碩士論文加值系統

特徵偵測演算法廣泛地應用在影像處裡、影像辨識和電腦視覺中，常見的影像特徵有「點」、「線條」、「區域」，其中「點」特徵也就是物件的角點。由於角點不受到影像物件幾何變化的影響而且容易被肉眼辨識的特性，成為重要的影像特徵。因此，越來越多的角點偵測演算法不斷的被提出來。然而，有關於圓角點的影像辨識卻鮮少被研究討論，而我們發現到螺旋型壓縮彈簧是一個很好的圓角點研究對象，並且針對螺旋型壓縮彈簧影像提出一個圓角偵測演算法。
本論文提出一個圓角點偵測演算法運用在量測螺旋型壓縮彈簧的外徑上，此方法利用斜率的比對來尋找圓角點的位置所在。透過實驗結果和統計資料，這個方法能夠準確的偵測界於水平0度到45度之間的彈簧外徑圓角點，計算的外徑誤差小於0.3%。而且在方法步驟中並沒有太過複雜的運算，所以能快速地提供穩定且準確的結果。未來期望本論文之方法可發展至產業界，應用於工業精密彈簧之檢測工具上。

Feature detection is widely used in image processing, image recognition and machine vision. Points, lines and regions are usually understood as features. In addition, point features are such as object corners because of their variances are not to be impacted by geometry property, and they are simple to recognize for every man. Hence, more and more individual corner detections are proposed. However, rounded corners are seldom discussed in image recognition, and we find thathelicalcompressionspring is a great object of study. Furthermore, we will propose a rounded corner detection algorithm to detect helical compression spring image.
In this paper we propose a rounded corner detection for detecting outside diameter of helical compression spring. The method uses slope comparison to search sites of rounded corner on the helical compression spring image. Through experiments and statistics for computing the outside diameter of spring, this method can steadily detect the rounded corners between 0 degree and 45 degrees, and the deviation of diameter is less than 0.3 percent. Furthermore, it does not have complicated operations in steps, so it can provides stable and accurate results swiftly.

目錄
摘要 I
Abstract II
誌謝 III
目錄 IV
圖次 VII
表次 X
第1章、 緒論 1
1.1 前言 1
1.2 研究動機與目的 4
1.3 論文架構概述 5
第2章、 相關文獻 6
2.1 SRM05 演算法 6
2.2 K-cosine 演算法 7
2.3 Chord to Point Distance 演算法 10
2.4 Boundary based 演算法 13
第3章、 圓角點偵測演算法 16
3.1 圓角點偵測演算法概述 16
3.2 邊緣擷取 19
3.2.1 Freeman鏈碼輪廓追蹤 19
3.2.2 擷取邊緣 20
3.3 圓角點偵測演算法 25
3.3.1 偵測候選圓角點 27
3.3.2 候選圓角點分類分組 29
3.3.3 偵測圓角點 33
第4章、 實驗結果 37
4.1 實驗環境 37
4.2 實驗目的 38
4.3 圓角點偵測演算法實驗 39
4.3.1 實驗一：彈簧角度實驗 39
4.3.1.1 一般彈簧 39
4.3.1.2 疏鬆彈簧 42
4.3.1.3 緊密彈簧 45
4.3.2 實驗二：彈簧參數k實驗 49
4.3.2.1 一般彈簧 49
4.3.2.2 疏鬆彈簧 53
4.3.2.3 緊密彈簧 56
第5章、 結論 60
參考文獻 61

[1] 黃春融, 詹寶珠, "由影像處理到電腦視覺," 2003.
[2] B. Zitová and J. Flusser, "Image registration methods: a survey," in Image and Vision Computing, 2003, pp. 977-100.
[3] L. W. Leu, "Study on the Buckling of Helical Compression Springs under Compression and/or Torsion," Department of Mechanical Engineering, National Taiwan University of Science and Technology, 2010.
[4] M. Sarfraz, A. Rasheed, and Z. Muzaffar, "A novel linear time corner detection algorithm," in Computer Graphics, Imaging and Vision: New Trends, 2005. International Conference on, 2005, pp. 191-196.
[5] M. Sarfraz, "A rational spline with tension: some CAGD perspectives," in Information Visualization, 1998. Proceedings. 1998 IEEE Conference on, 1998, pp. 178-183.
[6] A. Rosenfeld and E. Johnston, "Angle detection on digital curves," IEEE Trans. Comp, vol. 22, pp. 875-878, 1973.
[7] T. H. Sun, "K-Cosine Corner Detection," Journal of Computers, vol. 3, pp. 16-22, July 2008.
[8] C. Wang, G. Sun, Y. Wang, and L. Xu, "An Improved Corner Detection Algorithm Based on Gaussian Smoothing," in Intelligent Computation Technology and Automation (ICICTA), 2010 International Conference on, 2010, pp. 536-539.
[9] T. Y. Phillips and R. A, "A method of curve partitioning using arc-chord distance," Pattern Recognition Letters, vol. 5, pp. 285-288, 1987.
[10] J. H. Han and T. Poston, "Chord-to-point distance accumulation and planar curvature: a new approach to discrete curvature," Pattern Recognition Letters, vol. 22, pp. 1133-1144, Aug 2001.
[11] M. Awrangjeb and G. J. Lu, "Robust Image Corner Detection Based on the Chord-to-Point Distance Accumulation Technique," IEEE Transactions on Multimedia, vol. 10, pp. 1059-1072, Oct 2008.
[12] H. H. Aghdam and A. A. P. Kazem, "A novel corner detector with integrated corner angle computation," in Systems, Signals and Image Processing, 2008. IWSSIP 2008. 15th International Conference on, 2008, pp. 319-322.
[13] M.-H. Yen, Y.-C. Maa, J. Chan, Z.-Y. Huang, and Y.-L. Lin, "R-radius Corner Detection by Using CircularMask," presented at the 2011 National Computer Symposium (NCS 2011), National Chiayi University,Chiayi City, Taiwan, 2011.
[14] M.-H. Yen, Y.-C. Maa, C.-H. Ting, H.-C. Ho, and L.-A. Chu, "R-radius Corner Detection for fish larvae counting system," presented at the Changhua-Yunlin-Chiayi University &; Collede Alliance, Tatung Institute Of Technology,Chiayi, Taiwan 2011.
[15] X. C. He and N. H. C. Yung, "Corner detector based on global and local curvature properties," Optical Engineering, vol. 47, May 2008.
[16] H. Freeman, "On the encoding of arbitrary geometric configurations," IRE Transactions, vol. 10, pp. 260-268, 1961.
[17] M. Awrangjeb, L. Guojun, C. S. Fraser, and M. Ravanbakhsh, "A Fast Corner Detector Based on the Chord-to-Point Distance Accumulation Technique," in Digital Image Computing: Techniques and Applications, 2009. DICTA '09., 2009, pp. 519-525.
[18] X. C. He and N. H. C. Yung, "Curvature scale space corner detector with adaptive threshold and dynamic region of support," in Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on, 2004, pp. 791-794 Vol.2.
[19] J. Koplowitz and S. Plante, "Corner Detection for Chain Coded Curves," Pattern Recognition, vol. 28, pp. 843-852, Jun 1995.
[20] M. Marji, R. Klette, and P. Siy, "Corner Detection and Curve Partitioning Using Arc-Chord Distance.
Combinatorial Image Analysis." vol. 3322, R. Klette and J. Žunic, Eds., ed: Springer Berlin / Heidelberg, 2005, pp. 512-521.
[21] M. Sarfraz, A. Masood, and M. R. Asim, "A New Approach to Corner Detection," in Computer Vision and Graphics, 2006, pp. 528-533.
[22] P. Soo-Chang and D. Jian-Jiun, "New corner detection algorithm by tangent and vertical axes and case table," in Image Processing, 2005. ICIP 2005. IEEE International Conference on, 2005, pp. I-365-8.