國立高雄大學圖資館 |

語系: 繁體中文

說明(常見問題)

圖資館首頁

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Image segmentation/registration: A v...

Chen, Ping-Feng.

Image segmentation/registration: A variational framework for two-dimensional and three-dimensional applications.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Image segmentation/registration: A variational framework for two-dimensional and three-dimensional applications.
作者:	Chen, Ping-Feng.
面頁冊數:	128 p.
附註:	Source: Dissertation Abstracts International, Volume: 70-01, Section: B, page: 0529.
附註:	Adviser: Hamid Krim.
Contained By:	Dissertation Abstracts International70-01B.
標題:	Engineering, Electronics and Electrical.
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3345343
ISBN:	9781109005851

Image segmentation/registration: A variational framework for two-dimensional and three-dimensional applications.
Chen, Ping-Feng.

Image segmentation/registration: A variational framework for two-dimensional and three-dimensional applications. - 128 p.

Source: Dissertation Abstracts International, Volume: 70-01, Section: B, page: 0529.

Thesis (Ph.D.)--North Carolina State University, 2009.

Segmentation lands itself in the middle level of a computer vision system that it extracts boundary features in images. An accurate extraction of features will lead to the success of later higher level processes such as classification and recognition. Registration, on the other hand, is intimately intertwined with segmentation. An accurate allocation of edges, which are used as feature points, may increase the performance of registration. Whenever a single modality is not sufficient for segmentation and the resort to multi-spectral images is needed, and perfect alignment of these multi-spectral images will also facilitate the segmentation task.

ISBN: 9781109005851Subjects--Topical Terms:

226981
Engineering, Electronics and Electrical.

Image segmentation/registration: A variational framework for two-dimensional and three-dimensional applications.
LDR:03326nmm 2200301 4500 001 280704
005 20110119094933.5
008 110301s2009 ||||||||||||||||| ||eng d
020 $a 9781109005851
035 $a (UMI)AAI3345343
035 $a AAI3345343
040 $a UMI $c UMI
100 1 $a Chen, Ping-Feng. $3 492762
245 1 0 $a Image segmentation/registration: A variational framework for two-dimensional and three-dimensional applications.
300 $a 128 p.
500 $a Source: Dissertation Abstracts International, Volume: 70-01, Section: B, page: 0529.
500 $a Adviser: Hamid Krim.
502 $a Thesis (Ph.D.)--North Carolina State University, 2009.
520 $a Segmentation lands itself in the middle level of a computer vision system that it extracts boundary features in images. An accurate extraction of features will lead to the success of later higher level processes such as classification and recognition. Registration, on the other hand, is intimately intertwined with segmentation. An accurate allocation of edges, which are used as feature points, may increase the performance of registration. Whenever a single modality is not sufficient for segmentation and the resort to multi-spectral images is needed, and perfect alignment of these multi-spectral images will also facilitate the segmentation task.
520 $a In this thesis we propose segmentation and registration methods corresponding to different real applications. In the first biomedical application we propose a constrained Mumford-Shah type energy functional incorporated with an information-theoretic view and tuning weights. This model characterizes higher-order statistical properties of data and give a probabilistic flavor to our segmentation. It successfully segmented T1-Maps and T1-weighted images in both 2-D and 3-D. Validation of experts' manual segmentations also shows our method outperform most other techniques. Moreover we propose a joint radiofrequency (RF) -inhomogeneity calibration method to correct the non-uniformity of RF filed for accurate T1-Map generation.
520 $a We propose a multi-phase joint segmentation and registration technique (MPJSR) for mid-range layered imageries in the second application. Our method in particular may bring the objects of interest in a pair of layered images into perfect alignment and delineate the boundaries simultaneously. Based on our technique, we furthermore tackle the tracking problem for layered videos. By calculating a constrained optical flow between consecutive frames, a prediction for the contour initialization may be made in the next frame to expedite and increase the segmentation performance.
520 $a In the third application we took a step further after segmentation and registration. The study of canonical views of multiple range images launches from the assumption that the segmentation and registration between multiple range images are carried out. We propose using two methods: minimum description length (MDL) criterion and compressive sensing approaches, to determine the canonical views for a 3-D object.
590 $a School code: 0155.
650 4 $a Engineering, Electronics and Electrical. $3 226981
690 $a 0544
710 2 $a North Carolina State University. $3 492763
773 0 $t Dissertation Abstracts International $g 70-01B.
790 1 0 $a Krim, Hamid, $e advisor
790 $a 0155
791 $a Ph.D.
792 $a 2009
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3345343