臺灣博碩士論文加值系統

影像處理中，影像區分(Image Segmentation)技術可對影像中感興趣區域(Region of Interest, ROI)進行偵測並區分出影像物件供給後續處理，而輪廓擷取則是影像區分之主要處理方法之一，一般而言，區分出來的準確率會影響後續的運用結果。影像區分方法運用在工業電腦視覺檢測或其它具低階處理器機器上，除提升影像區分方法的準確率外，仍需考量到演算法的複雜度及自動化操作等因素。因此，本研究提出一個輪廓擷取方法，為除去人為設定初始點的限制，首先透過自動初始輪廓點選擇機制取得輪廓追蹤所需的追蹤起始點，接著再依據所取得的兩兩初始輪廓點之間像素之梯度變化及距離關係進行輪廓追蹤將輪廓取出。本方法透過實驗證實初始輪廓點選擇機制相較於其它方法可以取得較佳的初始輪廓點位置，而在兩兩初始輪廓點之間的區段輪廓追蹤上亦能準確取得物件區段輪廓並結合成為封閉輪廓。

Image segmentation is a technique which is used to segment region of interest in the image for further image processing. In general, the accuracy of segmentation result would affect result of further image processing or applications. Contour extraction is one of the most important image segmentation methods. When applying contour extraction to application of industrial inspection or machine vision with low-level processor, we not only consider accuracy but also consider automation and computational complexity. In this study, a contour extraction method is proposed, which consist of two parts. The first part is an automatic initial contour point selection mechanism for finding the initial contour points of contour segmental method for the second part of segmental contour tracing method, where contour pixels is obtain according to gradient value, direction and distance along two initial contour points. Finally, the result of the proposed method is compared with other methods.

中文摘要 i
Abstract ii
致謝 iii
目錄 iv
圖目錄 vii
表目錄 x
第一章 緒論 1
第一節 研究背景 1
第二節 問題描述 3
第三節 研究貢獻 5
第四節 章節架構 6
第二章 相關研究 7
第一節 邊緣導向 8
第二節 區域導向 11
第三節 模型導向 15
第四節 小結 17
第三章 研究架構 18
第一節 初始輪廓點選擇機制 19
第二節 區段式輪廓追蹤機制 30
第四章 實驗結果 36
第一節 初始輪廓點選擇比較方法及參數介紹 36
第二節 初始輪廓點選擇實驗結果與討論 40
第三節 抹除假初始輪廓點機制 58
第四節 輪廓追蹤比較方法及參數介紹 60
第五節 輪廓追蹤法實驗結果及討論 63
第五章 結論與未來工作 78
第一節 結論 78
第二節 未來工作 79
參考文獻 80

[1] J. Canny, "A Computational Approach to Edge Detection," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. PAMI-8, pp. 679-698, 1986.

[2] B. D. Chen and P. Siy, "Forward/backward contour tracing with feedback," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 9, pp. 438-446, 1987.

[3] X. Chenyang and J. L. Prince, "Gradient vector flow: a new external force for snakes," in Proc. IEEE Computer Society Conf., Computer Vision and Pattern Recognition Proceedings, pp. 66-71, 1997.

[4] Y. Fan, C. Liu, B. Zhang, and Z. Pan, "An Improved Algorithm of Contour Initialization in Active Contour Model," in Proc. Fourth International Conf., Image and Graphics, pp. 337-341, 2007.

[5] T. Huang, G. Yang, and G. Tang, "A fast two-dimensional median filtering algorithm," IEEE Trans. Acoustics, Speech and Signal, vol. 27, pp. 13-18, 1979.

[6] P. Jian-Jia, T. Yuan-Yan, and P. Bao-Chang, "The algorithm of fast mean filtering," in Proc. International Conf., Wavelet Analysis and Pattern Recognition, pp. 244-248, 2007

[7] T. Jinshan, E. Peli, and S. Acton, "Image enhancement using a contrast measure in the compressed domain," IEEE, Signal Processing Letters, vol. 10, pp. 289-292, 2003.

[8] M. Kass, A. Witkin, and D. Terzopoulos, "Snakes: Active contour models " International Journal of Computer Vision, vol. 1, pp. 321-331, 1988.

[9] C. Kirbas and F. Quek, "A review of vessel extraction techniques and algorithms," ACM Computing Surveys, vol. 36, pp. 81-121, 2004.

[10] W. Liu, S. Liang Yong, Y. Ren Xian, and P. Duan, "A New Approach for Extracting the Contour of an ROI in Medical Images," in Proc. International Conf., Advanced Computer Theory and Engineering, pp. 1025-1029, 2008.

[11] A. Mehnert and P. Jackway, "An improved seeded region growing algorithm," Pattern Recognition Letters, vol. 18, pp. 1065-1071, 1997.

[12] K. A. Panetta, E. J. Wharton, and S. S. Agaian, "Human Visual System-Based Image Enhancement and Logarithmic Contrast Measure," IEEE Trans. Systems, Man, and Cybernetics, Part B: Cybernetics, vol. 38, pp. 174-188, 2008.

[13] T. Pavlidis and S. L. Horowitz, "Segmentation of Plane Curves," IEEE Trans. Computers, vol. C-23, pp. 860-870, 1974.

[14] M. Sakalli, K. M. Lam, and Y. Hong, "A faster converging snake algorithm to locate object boundaries," IEEE Trans. Image Processing, vol. 15, pp. 1182-1191, 2006.

[15] I. E. Sobel, "Camera models and machine perception," Stanford University, 1970, pp. 99.

[16] T. N. Tan, "Rotation invariant texture features and their use in automatic script identification," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, pp. 751-756, 1998.

[17] W. Yu, Z. Jinjin, Z. Hongjun, and S. Lianguan, "Medical image processing by denoising and contour extraction," in Proc. International Conf., Information and Automation, pp. 618-623, 2008.

[18] H. C. van Assen, M. Egmont-Petersen, and J. H. C. Reiber, "Accurate object localization in gray level images using the center of gravity measure: accuracy versus precision," IEEE Trans. Image Processing, vol. 11, pp. 1379-1384, 2002.

[19] D.Y. Chan, R. C. Hsu, J.C. Jhuo, B.W. Kao, and C.T. Liu, "Polygon Approximation for Snake Initialization in Noisy Image," in Proc. International Workshop, Computer Vision and Its Application to Image Media Processing, 2009.

[20] P. C. Yuen, G. C. Feng, and J. P. Zhou, "A contour detection method: Initialization and contour model," Pattern Recognition Letters, vol. 20, pp. 141-148, 1999.

[21] R. C. Gonzalez, R. E. Woods, “Digital Image Processing (2nd Edition)” Prentice Hall, 2002.

[22] 何清人，“數學(三) ”，東大圖書公司，民國77年。

[23] 張真誠，黃國峰，陳同孝，”電子影像技術”，旗標出版社，民國92年。

[24] 黃友訊譯，“解析幾何數學(上) ”，徐氏基金會，民國76年。

[25] 戴顯權、陳瀅如、王春清，“多媒體通訊原理、標準與系統”，紳藍出版社，民國95年。