東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Object segmentation using shape cons...

Wang, Jingbin.

FindBook

Google Book

Amazon

博客來

Object segmentation using shape constraints.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Object segmentation using shape constraints./
作者:	Wang, Jingbin.
面頁冊數:	148 p.
附註:	Source: Dissertation Abstracts International, Volume: 68-03, Section: B, page: 1743.
Contained By:	Dissertation Abstracts International68-03B.
標題:	Computer Science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3254479

Object segmentation using shape constraints.
Wang, Jingbin.

Object segmentation using shape constraints. - 148 p.

Source: Dissertation Abstracts International, Volume: 68-03, Section: B, page: 1743.

Thesis (Ph.D.)--Boston University, 2007.

Segmenting and recognizing objects from images in the presence of noise, clutter and occlusions is an important and challenging problem in computer vision. Strict low-level, bottom-up techniques that address this problem cannot provide good interpretations of images for the purpose of object identification. A solution strategy is to incorporate high-level prior knowledge, such as shape constraints, into existing low-level visual routines, a methodology that this thesis investigates. The thesis provides three approaches that are based on variational approximation, stochastic sampling and dynamic programming, respectively. The first method applies a shape-based curve-growing model to segment the major pulmonary fissures on thin-section computed tomography. The employed curve-growing process is influenced by both image features and prior knowledge of the shape of the fissures. An adaptive regularization mechanism effectively balances these influences using an entropy measure. The second method identifies target objects in images by using prior information about object shape, represented in a multi-scale curvature form, and by grouping oversegmented image regions. The problem is formulated in a unified probabilistic framework, and image segmentation and object identification are accomplished simultaneously by a stochastic Markov Chain Monte Carlo mechanism. The third method employs Hidden State Shape Models, a variant of Hidden Markov Models, for detecting instances of object classes that exhibit variable shape structure. The term "variable shape structure" is used to characterize object classes in which some object parts can be repeated an arbitrary number of times, some parts can be optional, and some parts can have several alternative appearances. The thesis presents a detection method for finding instances of such object classes based on dynamic programming. Experimental results for the three proposed methods suggest that effective object segmentation can be achieved by introducing shape constraints.Subjects--Topical Terms:

626642
Computer Science.

Object segmentation using shape constraints.
LDR:02832nmm 2200253 4500 001 1833881
005 20071114145437.5
008 130610s2007 eng d
035 $a (UMI)AAI3254479
035 $a AAI3254479
040 $a UMI $c UMI
100 1 $a Wang, Jingbin. $3 1017602
245 1 0 $a Object segmentation using shape constraints.
300 $a 148 p.
500 $a Source: Dissertation Abstracts International, Volume: 68-03, Section: B, page: 1743.
500 $a Adviser: Margrit Betke.
502 $a Thesis (Ph.D.)--Boston University, 2007.
520 $a Segmenting and recognizing objects from images in the presence of noise, clutter and occlusions is an important and challenging problem in computer vision. Strict low-level, bottom-up techniques that address this problem cannot provide good interpretations of images for the purpose of object identification. A solution strategy is to incorporate high-level prior knowledge, such as shape constraints, into existing low-level visual routines, a methodology that this thesis investigates. The thesis provides three approaches that are based on variational approximation, stochastic sampling and dynamic programming, respectively. The first method applies a shape-based curve-growing model to segment the major pulmonary fissures on thin-section computed tomography. The employed curve-growing process is influenced by both image features and prior knowledge of the shape of the fissures. An adaptive regularization mechanism effectively balances these influences using an entropy measure. The second method identifies target objects in images by using prior information about object shape, represented in a multi-scale curvature form, and by grouping oversegmented image regions. The problem is formulated in a unified probabilistic framework, and image segmentation and object identification are accomplished simultaneously by a stochastic Markov Chain Monte Carlo mechanism. The third method employs Hidden State Shape Models, a variant of Hidden Markov Models, for detecting instances of object classes that exhibit variable shape structure. The term "variable shape structure" is used to characterize object classes in which some object parts can be repeated an arbitrary number of times, some parts can be optional, and some parts can have several alternative appearances. The thesis presents a detection method for finding instances of such object classes based on dynamic programming. Experimental results for the three proposed methods suggest that effective object segmentation can be achieved by introducing shape constraints.
590 $a School code: 0017.
650 4 $a Computer Science. $3 626642
690 $a 0984
710 2 0 $a Boston University. $3 1017454
773 0 $t Dissertation Abstracts International $g 68-03B.
790 1 0 $a Betke, Margrit, $e advisor
790 $a 0017
791 $a Ph.D.
792 $a 2007
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3254479