Multi-resolution feature extraction from Gabor filtered images

Author

Rizki, Mateen M. ; Tamburino, Louis A. ; ZMUDA, MICHAEL A.

Author_Institution

Dept. of Comput. Sci. & Eng., Wright State Univ., Dayton, OH, USA

fYear

1993

fDate

24-28 May 1993

Firstpage

819

Abstract

In this paper, we describe a hybrid learning system which combines a genetic algorithm with a neural network to classify grayscale images. The system operates on multi-resolution images which are formed by applying Gabor filters to a set of input images. The genetic algorithm evolves morphological probes that sample the multi-resolution images, and the perceptron algorithm then evaluates the extracted features. We demonstrate the use of this system by discriminating images of model tanks from other military vehicles. A multiplicity of accurate solutions, consisting of sparse morphological probes, are generated

Keywords

feature extraction; image recognition; learning (artificial intelligence); military computing; military systems; neural nets; Gabor filtered images; Gabor filters; Gabor stack preparation; genetic algorithm; grayscale images; hybrid learning system; military vehicles; model tanks; morphological probes; multi-resolution feature extraction; multi-resolution images; neural network; perceptron algorithm; sparse morphological probes; Aerospace electronics; Detectors; Feature extraction; Gabor filters; Genetic algorithms; Gray-scale; Image recognition; Probes; Testing; Vehicles;

fLanguage

English

Publisher

ieee

Conference_Titel

Aerospace and Electronics Conference, 1993. NAECON 1993., Proceedings of the IEEE 1993 National

Conference_Location

Dayton, OH

Print_ISBN

0-7803-1295-3

Type

conf

DOI

10.1109/NAECON.1993.290837

Filename

290837