Generation of feature detectors for texture discrimination by genetic search

Author

Bala, J.W. ; De Jong, K.

Author_Institution

Center for Artificial Intelligence, George Mason Univ., Fairfax, VA, USA

fYear

1990

fDate

6-9 Nov 1990

Firstpage

812

Lastpage

818

Abstract

A genetic-algorithm-based methodology for learning a set of feature detectors for texture discrimination is presented. This methodology is incorporated into a vision system that learns to classify noisy examples of different texture classes by evolving populations of simple and texture-specific local spatial feature detectors. The results of preliminary work confirm the utility of the genetic algorithm in solving problems within the specified domain

Keywords

computerised pattern recognition; computerised picture processing; genetic algorithms; learning systems; search problems; feature detectors; genetic search; genetic-algorithm-based methodology; noisy examples; texture classes; texture discrimination; texture-specific local spatial feature detectors; vision system; Artificial intelligence; Computer vision; Detectors; Feature extraction; Genetic algorithms; Image texture analysis; Learning; Machine vision; Pattern recognition; Prototypes;

fLanguage

English

Publisher

ieee

Conference_Titel

Tools for Artificial Intelligence, 1990.,Proceedings of the 2nd International IEEE Conference on

Conference_Location

Herndon, VA

Print_ISBN

0-8186-2084-6

Type

conf

DOI

10.1109/TAI.1990.130443

Filename

130443

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=3062128