UWSpace is currently experiencing technical difficulties resulting from its recent migration to a new version of its software. These technical issues are not affecting the submission and browse features of the site. UWaterloo community members may continue submitting items to UWSpace. We apologize for the inconvenience, and are actively working to resolve these technical issues.
 

Evolutionary Design for Computational Visual Attention

Thumbnail Image

Files

ndbbruce2003.pdf (1.06 MB)

Date

2003

Authors

Bruce, Neil

Journal Title

Journal ISSN

Volume Title

Publisher

University of Waterloo

Abstract

A new framework for simulating the visual attention system in primates is introduced. The proposed architecture is an abstraction of existing approaches influenced by the work of Koch and Ullman, and Tompa. Each stage of the attentional hierarchy is chosen with consideration for both psychophysics and mathematical optimality. A set of attentional operators are derived that act on basic image channels of intensity, hue and orientation to produce maps representing perceptual importance of each image pixel. The development of such operators is realized within the context of a genetic optimization. The model includes the notion of an information domain where feature maps are transformed to a domain that more closely corresponds to the human visual system. A careful analysis of various issues including feature extraction, density estimation and data fusion is presented within the context of the visual attention problem.

Description

Keywords

Systems Design, visual attention, genetic algorithms, image processing, image analysis, information theory, learning systems, machine vision, cognitive science

LC Keywords

Citation

URI

http://hdl.handle.net/10012/900

Collections

Theses
Systems Design Engineering