(3.238.174.50) 您好!臺灣時間:2021/04/18 16:59
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:吳佩珊
論文名稱:利用自主修正主動式輪廓完成雜訊影像之複雜邊界切割
論文名稱(外文):Self-Rectification Active Contour for Complex-Boundary Segmentation in Noisy Image
指導教授:章定遠
學位類別:碩士
校院名稱:國立嘉義大學
系所名稱:資訊工程學系研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2011
畢業學年度:99
語文別:中文
論文頁數:56
中文關鍵詞:蛇狀形變套索模型(snake)、snake初始化、snake修正
外文關鍵詞:Active contour model (snake)、snake initialization、snake rectification
相關次數:
  • 被引用被引用:0
  • 點閱點閱:174
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
傳統動態輪廓模型提供了很有用的工具去處理許多電腦視覺的工作,如:影像切割、視訊物件形狀擷取和醫學影像處理的問題。然而傳統動態輪廓模型非常依靠影像局部的資訊,不管這個資訊是適當的或不適當的。除此之外一般動態輪廓模型對於輪廓初始值的設定是非常敏感的,為了改進此缺點而使輪廓能夠更符合影像物件,本研究提出了一個物件切割機制,以邊緣引導修正適應性蛇狀形變套索(edge-conducted rectification adaptive snake, ECRA-snake)來切割複雜邊界於雜訊影像中。其內含三個階段,首先,以快速均勻分散來執行初始化做為snake的初始輪廓點,第二階段則以邊緣引導的演進(edge-conducted evolution, ECE)是主要部份來適應性的去調整模型係數,ECE本身做適應性調整其根據顯著的邊界特性而獲得更好的追蹤曲線吻合度。在ECE收斂後,以方向性所引起的修正演進(direction-induced rectification evolution, DIRE)為藉由特別處理過的snake力量方向和張力權重的初始值來修正不正確邊界的snake片段。這三個階段構成ECRA-snake是用來協調以加強控制snake模型能切割出高曲率的物件邊界。
Active contour model provides a powerful tool to deal with computer vision tasks such as image segmentation, video-object shape extraction, and medical image. But it heavily depends on image’s local information no matter how inappropriate the information is. Besides, in general, snake models are very sensitive to position initialization. In order to improve the Active contour model to fit the image object better. In this study, we propose a contour-fitness improved adaptive snake, namely, edge-conducted rectification adaptive snake (ECRA-snake) for segmenting complex-boundary objects in the noisy image. The ECRA-snake includes three ingredients. Firstly, a fast evenly-distributed initialization is performed for robust object-area marking. The second ingredient called edge-conducted evolution (ECE) is the main part, where the adaptations of model coefficients can accommodate ECE itself to the characteristics of salient edges for better curve fitting in tracking. Following ECE, a direction-induced rectification evolution (DIRE) will correct boundary-unmatched snake fragments by specially handling the initializations of their snake-force direction and tensile-force weighting. The three stages constructing the ECRA-snake are coordinated to enhance the control of snake model for segmenting the object of high-curvature boundaries.
中文摘要 i
Abstract ii
致謝 iii
目錄 iv
表目錄 ix
第一章 緒論 1
1.1 研究背景 1
1.2 問題描述 3
1.3 章節架構 5
第二章 相關研究 6
2.1 主動式輪廓模型相關研究 7
2.1.1 傳統主動式輪廓模型 7
2.1.2 氣球模型 8
2.1.3 梯度向量流主動式輪廓模型 8
2.1.4 方向性蛇形動態模型 9
2.2 初始點選擇相關研究 11
2.2.1 Yuen et.al.的自動化找出初始點 11
2.3 近年來研究 11
2.4 小結 13
第三章 研究方法 14
3.1 ECRA-snake初始化輪廓錨點選擇 16
3.2 以邊緣引導修正適應性蛇狀形變套索(ECRA-snake)模型 21
3.2.1 ECRA-snake 模型參數 22
3.2.2 輪廓吻合度的提高經由適應性調整內部力量的權重係數 25
3.2.3 適應性阻尼係數(Damping Factors) 26
3.2.4 修復不合適形變 27
3.3 以方向性引起的修正演進(DIRE) 28
3.3.1 區別出可疑吻合snaxel(SMS) 28
3.3.2 以明確的力量方向和權重的初始值為基礎來達成DIRE 32
第四章 實驗結果 35
4.1 演算法執行結果分析 35
4.1.1 初始化輪廓錨點選擇(BBSS)方法 35
4.1.2 以邊緣引導的演進(ECE)方法 36
4.1.3 以方向性所引起的修正演進(DIRE)方法 36
4.2 初始輪廓點選擇比較方法及參數介紹 37
4.2.1 初始點選擇比較方法 37
4.2.2 比較參數 38
4.2.3 實驗結果 38
4.3 輪廓追蹤比較方法及參數介紹 45
4.3.1 輪廓追蹤比較方法 45
4.3.2 比較參數設置 45
4.3.3 實驗結果 46
4.3.4 張力和彎曲力權重的初始值 49
第五章 結論與未來工作 53
5.1 結論 53
5.2 未來工作 54
參考文獻 55


[1] A. Mishra and A. Wong, “KPAC: A kernel-based parametric active contour method for fast image segmentation,” IEEE Signal Processing Letters, Vol. 17, pp. 312-315, 2010.
[2] A. Neumann, “Graphical gaussian shape models and their application to image segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 25, No. 3, pp. 316-329, Mar. 2003.
[3] B Wu, M. Xie, G. Li and J. Gao, “Medical image segmentation based on GVF snake model,” International Conference on Intelligent Computation Technology and Automation, Vol. 1, pp. 637-640, 2009.
[4] D. Murray and A. Basu,“Motion tracking with an active camera,” IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol. 16, No. 5, pp. 449-459, May 1994.
[5] F. J. Guerrero, V. Masero, J. M. Leon-Rojas and J. Moreno, “Multilure active contours,” ACM Symposium on Applied Computing, pp.247-254, 2005.
[6] H. G. Kaganami and Z. Beiji, “Region-based segmentation versus edge detection,” International Conference on Intelligent Information Hiding and Multimedia Signal Processing, pp. 1217-1221, 2009.
[7] H. G. Senel,“Topological gradient operator for edge detection,” IEEE International Conference on Image Processing, Vol. 3, pp. 61-64, 2007.
[8] H. Gao, W. C. Siu and C. H. Hou, “Improved techniques for automatic image segmentation,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 11, No. 12, pp. 1273-1280, Dec. 2001.
[9] H. P. Ng, K. W. C. Foong, S. H. Ong, P. S. Goh and W. L. Nowinski, “Medical image segmentation using feature-based GVF snake,” IEEE Conference on Engineering in Medicine and Biology Society, pp. 800-803, 2007.
[10] J. B. Xu, L. M. Po and C. K. Cheung, “Adaptive motion tracking block matching algorithm for video coding,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 9, No. 7, pp. 1025-1029, Oct. 1999.
[11] J. Cheng, R. Xue, Y. Liu and W. Lu, “Segmentation of mechanical images using improved active contour model,” IEEE International Conference on Industrial Technology, pp. 1-4, 2008.
[12] J. Hernandez, F. Prieto and T. Redarce, “Fast active contours for sampling,” IEEE Conference on Electronic, Robotics and Automotive Mechanics, Vol. 2, pp. 9-13, Sept. 2006.
[13] J. Liu and Y. H. Yang,“Multiresolution color image segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 16, No. 7, pp. 689-700, Jul. 1994.
[14] J. Ning, C. Wu, S. Liu and S. Yang, “NGVF: An improved external force field for active contour model,” Pattern Recognit. Letters, Vol. 28, pp. 58–63, 2007.
[15] L. D. Cohen, “On active contour models and balloons,”Computer Vision Graphics and Image Processing: Image Understanding, Vol. 53, No. 2, pp. 211-218, Mar. 1991.
[16] M. Kass, A.P. Witkin and D. Terzopoulos, “Snakes: Active contour models,” International Journal of Computer Vision, Vol. 1, pp. 321-331, 1988.
[17] 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, Feb. 1999.
[18] P. L. Correia and F. Pereira, “Objective evaluation of video segmentation quality,” IEEE Transactions on Image Processing, Vol. 12, No. 2, pp. 186-200, Feb. 2003.
[19] R. H. Davies, C. J. Twining, T. F. Cootes, J. C. Waterton and C. J. Taylor, “A minimum description length approach to statistical shape modeling,” IEEE Transactions on Medical Imaging, Vol. 21, No. 5, pp. 525-537, May 2002.
[20] S. Y. Chien, Y. W. Huang, B. Y. Hsieh, S. Y. Ma and L. G. Chen, “Fast video segmentation algorithm with shadow cancellation, global motion compensation, and adaptive threshold techniques,” IEEE Transactions on Multimedia, Vol. 6, No. 5, pp. 732-748, Oct. 2004.
[21] T. Uchiyama and M. A. Arbib, “Color image segmentation using competitive learning,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 16, No. 12, pp. 1197-1206, Dec. 1994.
[22] U. Ozertem and D. Erdogmus, “Nonparametric snakes,” IEEE Transactions on Image Processing, Vol. 16, No.9, pp. 2361-2368, Sept. 2007.
[23] H. Park, T. Schoepflin and Y. Kim, “Active contour model with gradient directional information: Directional snake,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 11, No. 2, pp. 252-256, Feb. 2001.
[24] X. Chenyang and J. L. Prince, “Gradient vector flow: A new external force for snakes,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition Proceedings, pp. 66-71, 1997.
[25] X. Zhang, Y. Shan, W. Wei and Z. Zhu, “An image segmentation method based on improved watershed algorithm,” International Conference on Computational and Information Sciences, pp. 258-261, 2010.
[26] Y. Zhao, J. Liu, H. Li and G. Li, “Improved watershed algorithm for dowels image segmentation,” World Congress on Intelligent Control and Automation, pp. 7644-7648, 2008.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔