Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/24208
DC FieldValueLanguage
dc.contributor詹啟祥zh_TW
dc.contributorChi-Shiang Chanen_US
dc.contributor洪國龍zh_TW
dc.contributor吳憲珠zh_TW
dc.contributor黃國峰zh_TW
dc.contributorKuo-Lung Hungen_US
dc.contributorHsien-Chu Wuen_US
dc.contributorKuo-Feng Huangen_US
dc.contributor.advisor詹永寬zh_TW
dc.contributor.advisorYung-Kuan Chanen_US
dc.contributor.author席正平zh_TW
dc.contributor.authorHsi, Cheng-Pingen_US
dc.contributor.other中興大學zh_TW
dc.date2012zh_TW
dc.date.accessioned2014-06-06T07:22:22Z-
dc.date.available2014-06-06T07:22:22Z-
dc.identifierU0005-1707201118462200zh_TW
dc.identifier.citation[1]F. Benmansour, L. D. Cohen, “Fast Object Segmentation by Growing Minimal Paths from a Single Point on 2D or 3D Images,” Journal of Mathematical Imaging and Vision, pp. 209-221, 2009. [2]J. Canny, “A Computational Approach to Edge Detection,”. IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-8, No. 6, pp. 679-698, November 1986. [3]R. C. Gonzalez, R. E. Woods, Digital Image Processing, Englewood Cliffs, NJ: Prentice-Hall, 2002. [4]M. Kass, A. Witkin, and D. Terzopoulos, “Snakes - Active Contour Models,” International Journal of Computer Vision, Vol. 1, No. 4, pp. 321-331, 1987. [5] C. L. Phillips, “The Level-Set Method,” MIT Undergraduate Journal of Mathematics, No. 1, pp. 155-164, June 1999. [6]S. Ravishankar, A. Jain, and A. Mittal, “Multi-Stage Contour Based Detection of Deformable Objects,” ECCV 2008, Part I, LNCS 5302, pp. 483-496, 2008. [7]C. Xu, J. L. Prince “Gradident Vector Flow: A New External Force for Snakes,” IEEE Computer Society Conference on Pattern Recognition, pp. 66-71, 1997. [8]J.A. Sethian, “Level Set Methods and Fast Marching Methods”, Cambridge: Cambridge, University Press, New York, 1999. [9]S. Osher, R. Fedkiw, “Level Set Methods and Dynamic Implicit Surfaces”, Springer-Verlag, New York, 2003.zh_TW
dc.identifier.urihttp://hdl.handle.net/11455/24208-
dc.description.abstract物件輪廓偵測在影像處理領域上扮演一個重要的角色。有許多著名的邊緣偵測及物件輪廓偵測例如Canny 邊緣偵測、ACM、 Level Set等。但是這些方法經常不能得到完全的物件邊界。在ACM Level Set 方法中需要使用者給予初始輪廓,並且初始輪廓會大大影響到最後偵測的結果。另外ACM與Level Set 方法會特別受到雜訊的影響。而Canny邊緣偵測不需要使用者設定一個初始輪廓,但是它會產生斷線問題的現象。為了解決斷線問題,因此本篇論文提出一個feature-based disconnected object contour segments (FBDOC) linker方法,本論文先用Canny邊緣偵測方法得到物件初始輪廓,然後我們方法會根據影像邊界特徵將斷線的地方連接,這些影像特徵包括影像灰階值差異量、連線兩點之間距離、梯度及梯度方向。實驗結果顯示我們的方法跟Level Set及ACM的方法比較可以得到更好的物件邊界結果。zh_TW
dc.description.abstractObject contour detection plays an important role in image processing. Many edge and object contour detectors have been proposed, such as, Canny edge detector, ACM, and level set methods. However, those detection methods cannot always obtain the edge and object contour completely. In the ACM and level set methods, the initial contour of object has to be specified by a user in advance, and the segmentation results highly depend on the given initial contour. In addition, the ACM and level set methods are significantly sensitive to noise. Although it does not need to give any initial contour of object for Canny edge detector, it may bring about “broken edge problem.” To solve the broken edge problem, a feature-based disconnected object contour segments (FBDOC) linker is provided in this thesis. For extracting objects from an image, in this thesis Canny edge detector is first used to detect the object contour, and then the FBDOC linker is employed to link the disconnected edge segments based on the features of the gray-level difference at vicinity of, the gradient and gradient direction on, and the length of the line segment connecting two disconnected edge segments. The experimental results show that the FBDOC linker can give more impressive object segmentation results than the level set method and ACM method do.en_US
dc.description.tableofcontentsAbstract (in Chinese) i Abstract (in English) ii Table of Contents iii List of Tables v List of Figures vi Chapter 1 Introduction 1 1.1 Background and Motivation 1 1.2 Organization of the Thesis 2 Chapter 2 Literature Reviews 3 2.1 Sobel Operator 3 2.2 Canny edge detection method 4 2.3 Action Contour Model (ACM) 7 Chapter 3 The Proposed FBDOC Method 9 3.1 FBDOC Linker 9 3.2 Endpoint Checking 11 3.3 Feature Extraction 12 3.3.1 The Length of L 13 3.3.2 The Gray-Level Difference of Li 14 3.3.3 The Gradient and Gradient Direction Feature(GDF) 15 3.4 Disconnected Edge Segments Filter 17 3.5 Spur Trimming 17 Chapter 4 Experimental Results 19 Chapter 5 Conclusions and Future Works 35 References 36en_US
dc.language.isoen_USzh_TW
dc.publisher資訊管理學系所zh_TW
dc.relation.urihttp://www.airitilibrary.com/Publication/alDetailedMesh1?DocID=U0005-1707201118462200en_US
dc.subjectfalse edge segmenten_US
dc.subject錯誤邊緣切割zh_TW
dc.subjectcanny edge detectoren_US
dc.subjectgradienten_US
dc.subjectgradient directionen_US
dc.subjectCanny 邊緣偵測zh_TW
dc.subject梯度zh_TW
dc.subject梯度方向zh_TW
dc.title以特徵為基礎之斷裂物件輪廓連結器zh_TW
dc.titleFeature-Based Disconnected Object Contour Linkeren_US
dc.typeThesis and Dissertationzh_TW
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.openairetypeThesis and Dissertation-
item.cerifentitytypePublications-
item.fulltextno fulltext-
item.languageiso639-1en_US-
item.grantfulltextnone-
Appears in Collections:資訊管理學系
Show simple item record
 
TAIR Related Article

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.