國立高雄大學圖資館 |

Language: English

Back

The perceptual organization of visual flows.

Record Type:	Electronic resources : Monograph/item
Title/Author:	The perceptual organization of visual flows.
Author:	Ben-Shahar, Ohad.
Description:	179 p.
Notes:	Director: Steven W. Zucker.
Notes:	Source: Dissertation Abstracts International, Volume: 64-10, Section: B, page: 5027.
Contained By:	Dissertation Abstracts International64-10B.
Subject:	Computer Science.
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3109375
ISBN:	0496569171

The perceptual organization of visual flows.
Ben-Shahar, Ohad.

The perceptual organization of visual flows. [electronic resource] - 179 p.

Director: Steven W. Zucker.

Thesis (Ph.D.)--Yale University, 2003.

Locally parallel dense patterns---visual flows---define a perceptually coherent structure of particular significance to perceptual organization. Geometrically, it is argued that a proper way to investigate these structures requires the frame field approach from differential geometry, a study that leads to the notion of visual flow curvatures and to constraints on their mutual behavior. These curvatures are then used to develop a theory, and a rigorous model, of visual flow "good continuation" that extends common terminology from Gestalt psychology and from computational studies of curves.

ISBN: 0496569171Subjects--Topical Terms:

212513
Computer Science.

The perceptual organization of visual flows.
LDR:02389nmm _2200265 _450 001 162285
005 20051017073430.5
008 230606s2003 eng d
020 $a 0496569171
035 $a 00148786
035 $a 162285
040 $a UnM $c UnM
100 0 $a Ben-Shahar, Ohad. $3 227412
245 1 4 $a The perceptual organization of visual flows. $h [electronic resource]
300 $a 179 p.
500 $a Director: Steven W. Zucker.
500 $a Source: Dissertation Abstracts International, Volume: 64-10, Section: B, page: 5027.
502 $a Thesis (Ph.D.)--Yale University, 2003.
520 # $a Locally parallel dense patterns---visual flows---define a perceptually coherent structure of particular significance to perceptual organization. Geometrically, it is argued that a proper way to investigate these structures requires the frame field approach from differential geometry, a study that leads to the notion of visual flow curvatures and to constraints on their mutual behavior. These curvatures are then used to develop a theory, and a rigorous model, of visual flow "good continuation" that extends common terminology from Gestalt psychology and from computational studies of curves.
520 # $a The geometrical theory is then applied in three ways. Firstly, psychophysical exploration of the role of visual flow curvatures in human perception shows that sensitivity to these curvatures greatly affects orientation-based texture segmentation. Secondly, a contextual framework for the computation of coherent visual flows from images is developed and applied to texture, shading, and color analysis. Unlike existing approaches, the proposed framework is able to handle both sparse, dense, and multivalued data sets, while preserving line and point singularities and rejecting large scale non-flow structures. Lastly, the geometrical theory is linked to the functional organization of primary visual cortex to accurately predict the distribution of long range horizontal connections and to support their identification with those obtained mathematically.
590 $a School code: 0265.
650 # 0 $a Computer Science. $3 212513
650 # 0 $a Psychology, Cognitive. $3 212507
710 0 # $a Yale University. $3 212430
773 0 # $g 64-10B. $t Dissertation Abstracts International
790 $a 0265
790 1 0 $a Zucker, Steven W., $e advisor
791 $a Ph.D.
792 $a 2003
856 4 0 $u http://libsw.nuk.edu.tw/login?url=http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3109375 $z http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3109375