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.<>
Multi-resolution feature extraction from Gabor filtered images
01.01.1993
697756 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Feature Extraction and Analysis of Handwritten Words in Gray-scale Images using Gabor Filters
British Library Conference Proceedings | 1994
|Gabor Filter Approach to Joint Feature Extraction and Target Recognition
Online Contents | 2009
|