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

Optimal visual search strategies usi...

The University of Texas at Austin., Electrical and Computer Engineering.

Linked to FindBook

Google Book

Amazon

博客來

Optimal visual search strategies using Natural Scene Statistics.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Optimal visual search strategies using Natural Scene Statistics./
Author:	Raj, Raghu G.
Description:	230 p.
Notes:	Adviser: Alan C. Bovik.
Contained By:	Dissertation Abstracts International68-12B.
Subject:	Engineering, Electronics and Electrical. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoeng/servlet/advanced?query=3290890
ISBN:	9780549349945

Optimal visual search strategies using Natural Scene Statistics.
Raj, Raghu G.

Optimal visual search strategies using Natural Scene Statistics. - 230 p.

Adviser: Alan C. Bovik.

Thesis (Ph.D.)--The University of Texas at Austin, 2007.

I present theoretical foundations and perform computational studies on optimal search strategies in natural scenes performed by foveated artificial vision systems, based on novel characterizations of Natural Scene Statistics (NSS).

ISBN: 9780549349945Subjects--Topical Terms:

626636
Engineering, Electronics and Electrical.

Optimal visual search strategies using Natural Scene Statistics.
LDR:03583nam 2200325 a 45 001 857529
005 20100712
008 100712s2007 ||||||||||||||||| ||eng d
020 $a 9780549349945
035 $a (UMI)AAI3290890
035 $a AAI3290890
040 $a UMI $c UMI
100 1 $a Raj, Raghu G. $3 1024483
245 1 0 $a Optimal visual search strategies using Natural Scene Statistics.
300 $a 230 p.
500 $a Adviser: Alan C. Bovik.
500 $a Source: Dissertation Abstracts International, Volume: 68-12, Section: B, page: 8272.
502 $a Thesis (Ph.D.)--The University of Texas at Austin, 2007.
520 $a I present theoretical foundations and perform computational studies on optimal search strategies in natural scenes performed by foveated artificial vision systems, based on novel characterizations of Natural Scene Statistics (NSS).
520 $a I first develop relevant theoretical bounds on the processing of foveated---more generally LSV-filtered (Linear Scale Variant)---signals, which provide a rigorous basis to linear post-processing operations performed on foveated images. The major contribution of this dissertation, however, lies in the discovery and elucidation of two major statistical characterizations of natural scenes and their subsequent deployment for devising optimal fixation strategies.
520 $a The first is a novel characterization of the contrast statistics of natural scenes, parameterized by the eccentricity at which each contrast level is measured across the LSV-filtered image. This formulation of contrast statistics finds natural application in devising fixation patterns that optimally extract contrast information from the image. I further demonstrate that the resulting fixation patterns are nearly optimal in the sense of minimizing the global MSE of the LSV-filtered image.
520 $a The second is the characterization of the non-stationary structure of natural images via the development of the concept of non-stationarity indices that measure the extent of non-stationarity across the image. The theoretical motivation of our approach lies in a novel characterization of image patch statistics I developed, called Multilinear Independent Component Analysis (MICA), wherein the statistical interactions between the pseudo-independent components are captured via a multilinear expansion of the joint probability density being modeled. This modeling technique enables the derivation of a theoretical measure of non-stationary in natural scenes that subsequently motivates computationally efficient non-stationarity indices---a variant of which is then deployed to furnish optimal texture-based fixations natural images. The fixation patterns generated by our information-theoretic approaches are quantitatively shown to match very well with human fixation patterns and offer considerable explanatory and predictive power over previously well-known fixation strategies.
520 $a These results point the way towards a unified information-theoretic understanding of low-level fixation processes; and further demonstrate the importance of incorporating low-level visual information into visual search strategies---thereby providing a foundation upon which high-level visual information relating to scene context and object structures can be incorporated.
590 $a School code: 0227.
650 4 $a Engineering, Electronics and Electrical. $3 626636
650 4 $a Engineering, System Science. $3 1018128
690 $a 0544
690 $a 0790
710 2 $a The University of Texas at Austin. $b Electrical and Computer Engineering. $3 1018445
773 0 $t Dissertation Abstracts International $g 68-12B.
790 $a 0227
790 1 0 $a Bovik, Alan C., $e advisor
791 $a Ph.D.
792 $a 2007
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoeng/servlet/advanced?query=3290890