東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Analysis of neighborhood relationshi...

Bhattacharya, Arnab.

Linked to FindBook

Google Book

Amazon

博客來

Analysis of neighborhood relationships in biomedical images.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Analysis of neighborhood relationships in biomedical images./
Author:	Bhattacharya, Arnab.
Description:	203 p.
Notes:	Adviser: Ambuj K. Singh.
Contained By:	Dissertation Abstracts International68-10B.
Subject:	Computer Science. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3283690
ISBN:	9780549268888

Analysis of neighborhood relationships in biomedical images.
Bhattacharya, Arnab.

Analysis of neighborhood relationships in biomedical images. - 203 p.

Adviser: Ambuj K. Singh.

Thesis (Ph.D.)--University of California, Santa Barbara, 2007.

Neighborhood analysis methods such as mentioned above will help scientists in pursuing new frontiers of life science, and will ultimately provide the impetus to make biomedical imaging a successful discipline.

ISBN: 9780549268888Subjects--Topical Terms:

626642
Computer Science.

Analysis of neighborhood relationships in biomedical images.
LDR:03215nam 2200337 a 45 001 963314
005 20110831
008 110831s2007 ||||||||||||||||| ||eng d
020 $a 9780549268888
035 $a (UMI)AAI3283690
035 $a AAI3283690
040 $a UMI $c UMI
100 1 $a Bhattacharya, Arnab. $3 1286377
245 1 0 $a Analysis of neighborhood relationships in biomedical images.
300 $a 203 p.
500 $a Adviser: Ambuj K. Singh.
500 $a Source: Dissertation Abstracts International, Volume: 68-10, Section: B, page: 6750.
502 $a Thesis (Ph.D.)--University of California, Santa Barbara, 2007.
520 $a Neighborhood analysis methods such as mentioned above will help scientists in pursuing new frontiers of life science, and will ultimately provide the impetus to make biomedical imaging a successful discipline.
520 $a The ability of biomedical images to capture spatial and temporal relationships not immediately available from other data sources make them vital in understanding the underlying processes of biology. Therefore, it is imperative to investigate and analyze the neighborhood relationships among the different image features and objects that exist at various levels in both space and time in biomedical images.
520 $a Spatial relationships exist in different levels, from among full images to regions inside the images to patterns inside the regions. The different temporal events from time-series images and videos are similarly related to each other based on their temporal position and localization. Finally, neighborhood associations exist among image datasets as well.
520 $a I first exhibit why spatial location of objects in biomedical images is significant for meaningful comparison. Then, I show how such spatial relationships can be encoded in the earth mover's distance and how image retrievals using it can be accelerated by using multi-resolution lower bounding index structures. I then highlight the importance of distinguishing between foreground and background in the context of region queries in biomedical images. I design a scoring mechanism to retrieve only the foreground matches for image query patterns. Next, I describe a mechanism to explore the relationships among the basic patterns in an image dataset by automatically constructing a visual vocabulary of the dataset. The visual vocabulary is useful in succinctly describing the content of an image dataset. Finally, I explore the temporal aspects of proximity. I discuss ways to classify sub-sequences of a time-series by examining the adjacency relationships between the consecutive events from the time-series. I also develop a general method of visualizing the relationships among different conditions by embedding their corresponding model parameters onto a two-dimensional plot.
590 $a School code: 0035.
650 4 $a Computer Science. $3 626642
690 $a 0984
710 2 $a University of California, Santa Barbara. $b Computer Science. $3 1018455
773 0 $t Dissertation Abstracts International $g 68-10B.
790 $a 0035
790 1 0 $a El Abbadi, Amr $e committee member
790 1 0 $a Manjunath, Bangalore S. $e committee member
790 1 0 $a Singh, Ambuj K., $e advisor
790 1 0 $a Wilson, Leslie $e committee member
791 $a Ph.D.
792 $a 2007
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3283690