臺灣博碩士論文加值系統

本論文中，首先探討了影像離散輪廓偵測【23】與關鍵點【22】是否都能完整的代表該影像的輪廓與重要的交點、角點與高曲率區域，並比較了第一級和第二級關鍵點的差異，也比較了第一級曲率輪廓與第二級曲率輪廓的相同相異之處，最後在本論文中，我們發展出一套有效的影像封閉輪廓擷取方法，而先前【22】舊有的輪廓獲得方式，不但無法有效的獲得能代表該影像的完整輪廓，且也無法解決輪廓斷裂點的問題，且生長範圍也被局限於9*9的範圍內，而本論文提出了精準的關鍵點、關鍵點的生長方向、與關鍵點生長臂膀的輪廓連結機制來擷取影像輪廓，以達到能簡單並有效的擷取影像的連續輪廓或邊線，並使此連續輪廓能簡易的代表該張原始影像中的邊線或輪廓。

The purpose of this thesis is to develop an image contour extraction scheme by grouping edges and key points. The key points are defined as corners, junctions, and high curvature points. Discrete contour points are detected by suppressing texture-like edges. The key points are obtained from both the first-stage and the second-stage Teager curvature energy extraction units. We have established a contour-linking algorithm started synchronously from all key points. In addition, the arms of each key point are generated by this linking process, which describe the directions of contours originated from the key point. Hence, the types of key points are delineated by their associated arms. We have also constructed an efficient representation of the closed contours by the key points after completing the linking procedure.

目錄

誌謝 i
摘要 ii
Abstract iii
目錄 iv
圖目錄 vi
表目錄 x
第一章 序論 1
1.1 簡介 1
1.2 研究動機 6
1.3 研究目標 9
1.4 文獻方法 9
1.5 研究方法與進行步驟 13
1.6 章節介紹 15
第二章 影像邊界輪廓模型與第二級Teagar 16
2.1 特徵擷取 16
2.2 輪廓模型 20
2.3 第二級Teagar能量組合 31
第三章 關鍵點 33
3.1 關鍵點之獲得 33
3.2 合併第一級與第二級之關鍵點 36
3.3交點、角點能量之提升 44
3.4 第二級曲率機制 49
3.5 關鍵點篩選機制 57
第四章 影像輪廓之擷取 66
4.1 關鍵點的生長方向 67
4.2 關鍵點矯正機制 73
4.3 生長臂膀的輪廓連結機制 77
4.4 影像封閉輪廓之獲得 83
第五章 實驗結果與討論 88
5.1 第二級曲率輪廓 88
5.2 精準的關鍵點 90
5.3 自然影像與人工影像輪廓擷取之測試 96
第六章 結論 102
參考文獻 103

[1]A. Alexandrov, "Corner detection overview and comparison," 2002.
[2]B. Robbins and R. Owens, "2D Feature detection via local energy," Image and Vision Computing, vol(15), pp.353-368, 1997.
[3]C. Hsin, H. T. Wang, and S. J. Shin, "Edge detection based on an adaptive local grey-level mapping," IPPR15th IPPR Conference on Computer Vision, Graphics, and Image Processing, Taiwan, R.O.C., Aug. 2002.
[4]C. Hsin, S. C. Chen, Y. P. Wang and S. H. Cheng, "Contour detection based on suppression of texture-like edges," IPPR16th IPPR Conference on Computer Vision, Graphics, and Image Processing, Taiwan, R.O.C., Aug. 2003. NSC 91-2219-E-035-002, 2002.
[5]F. Heitger, L. Rosenthaler, R. V. D. Heydt, E. Peterhans, and O. Kubler, “Simulation of neural contour mechanisms：from simple to end-stopped cells,” Vision Research, vol. 32(5), pp.963-981, 1992.
[6]J. Canny, "A computational approach to edge detection," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 8(6), pp.679-698, Nov. 1986.
[7]J. H. Elder and S. W. Zucker, "Local scale control for edge detection and blur estimation," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20(7), pp.699-716, 1998.
[8]K. Rangarajan, M. Shan, and D.V. Brackle, "Optimal corner detection," Computer Vision, Graphics, and Image Processing, vol. 48, pp.230-245, 1989.
[9]L. Kitchen and A. Rosenfeld, "Gary-level corner detection," Pattern Recognition Letters, vol. 1, pp.95-102, 1982.
[10]L. Rosenthaler, F. Heitger, O.Kubler and R.von der Heydt, "Detection of general edge and keypoints," In ECCV92, Springer-Verlag Lecture Notes in Computer Science, vol. 588, pp.78-86. Springer-Verlag, Santa Margherita Ligure, Italy., May 1992.
[11]M. S. Moore, R. Bernstein, and S. K. Mitra, "A generalization of the Teager algorithm," Processing IEEE Workshop on Nonlinear Signal Processing, Michigan, Sep. 1997.
[12]P. Kovesi, "Phase Congruency Detects Corners and Edges," School of Computer Science & Software Engineering, The University of Western Australia.
[13]P. Maragos, F. Kaiser, and F. Quatieri, “On amplitude and frequency demodulation using energy operators,” IEEE Transaction on Signal Processing, vol. 41(4), pp.3331-3340, 1993.
[14]P. Meer and B. Georgescu, "Edge detection with embedded confidence," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, pp.1351-1365, Dec. 2001.
[15]R. Deriche and G. Giraudon, "A computational approach for corner and vertex detection," Int’l J. Computer Vision, vol. 10(2), pp.101-124,1993.
[16]R. Hamila, J. Astola, F. A. Cheikh, M. Gabbouj and M. Renfors, “Teager Energy and the Ambiguity Function,” IEEE Transactions on Signal Processing, vol. 47(1), pp.260-262, Jan. 1999.
[17]R. P. Wurtz and T. Lourns, "Corner detection in color images through a multiscale combination of end-stopped nortical eells," Image and Vision Computing, vol. 18, pp.531-541, 2000.
[18]S. Ando, "Image field categorization and edge/corner detection from gradient covariance," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22(2), pp.179-190, 2000.
[19]S. Newsam, S. Bhagavathy, L. Fonseca, C. Kenney, and B. S. Manjunath, "Object based representations of spatial images," in Processing 51st International Aeronautical Congress, Rio de Janeiro, Brazil, Oct. 2000.
[20]W. Y. Ma and B. S. Manjunath, "Edge flow：a technique for boundary detection and segmentation," IEEE Transactions on Image Processing, vol. 9(8), pp.1375-1388, Aug. 2000.
[21]C. Hsin and F. H. Liao, “Textural feature extraction and texture reconstruction based on Gabor filter bank,” 逢甲大學通訊工程學系研究所碩士論文, 2005.
[22]C. Hsin and M. H. Yang, “Detection of image contours,” 逢甲大學通訊工程學系研究所碩士論文, 2005.
[23]C. Hsin and H. T. Chen, "Detection of image contours," 逢甲大學通訊工程學系研究所碩士論文, 2004.
[24]C. Hsin and H. T. Wang, "Image feature detection based on local gray-level modification," 逢甲大學通訊工程學系研究所碩士論文, 2002.
[25]陳家祥, “Image Compression based on theories of Gaussian Frames and Feature Extraction,” 逢甲大學電子工程研究所碩士學位論文, 1998.
[26]張獻堂, “Nonlinear image feature extraction theory on edges and lines,” 逢甲大學電子工程研究所碩士學位論文, 2002.