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

First steps towards extracting objec...

Shah, Viral H.

Linked to FindBook

Google Book

Amazon

博客來

First steps towards extracting object models from natural scenes.

Record Type:	Electronic resources : Monograph/item
Title/Author:	First steps towards extracting object models from natural scenes./
Author:	Shah, Viral H.
Description:	40 p.
Notes:	Source: Masters Abstracts International, Volume: 44-01, page: 0407.
Contained By:	Masters Abstracts International44-01.
Subject:	Computer Science. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=1427984
ISBN:	9780542209291

First steps towards extracting object models from natural scenes.
Shah, Viral H.

First steps towards extracting object models from natural scenes. - 40 p.

Source: Masters Abstracts International, Volume: 44-01, page: 0407.

Thesis (M.S.)--University of Southern California, 2005.

This dissertation presents the first steps towards a general method of extracting features from images to fulfill the two-fold task of Object Classification and Recognition. We consider looking at humans as a test case and perform recognition tasks. Two methods were developed for the purpose. The first method was provided with minimal a priori information about the structure of humans, in the form of fixed node positions within bounding boxes around the major body parts. This method gave rise to several problems and the system failed in cases of partial occlusion. Therefore a second method was developed which extracted information on from a vast sampling of points placed on the segmented part of the image. This method showed much better results in cases of partial occlusion.

ISBN: 9780542209291Subjects--Topical Terms:

626642
Computer Science.

First steps towards extracting object models from natural scenes.
LDR:01624nmm 2200265 4500 001 1820325
005 20061023071506.5
008 130610s2005 eng d
020 $a 9780542209291
035 $a (UnM)AAI1427984
035 $a AAI1427984
040 $a UnM $c UnM
100 1 $a Shah, Viral H. $3 1909555
245 1 0 $a First steps towards extracting object models from natural scenes.
300 $a 40 p.
500 $a Source: Masters Abstracts International, Volume: 44-01, page: 0407.
500 $a Adviser: Antonio Ortega.
502 $a Thesis (M.S.)--University of Southern California, 2005.
520 $a This dissertation presents the first steps towards a general method of extracting features from images to fulfill the two-fold task of Object Classification and Recognition. We consider looking at humans as a test case and perform recognition tasks. Two methods were developed for the purpose. The first method was provided with minimal a priori information about the structure of humans, in the form of fixed node positions within bounding boxes around the major body parts. This method gave rise to several problems and the system failed in cases of partial occlusion. Therefore a second method was developed which extracted information on from a vast sampling of points placed on the segmented part of the image. This method showed much better results in cases of partial occlusion.
590 $a School code: 0208.
650 4 $a Computer Science. $3 626642
690 $a 0984
710 2 0 $a University of Southern California. $3 700129
773 0 $t Masters Abstracts International $g 44-01.
790 1 0 $a Ortega, Antonio, $e advisor
790 $a 0208
791 $a M.S.
792 $a 2005
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=1427984