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.<>


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Multi-resolution feature extraction from Gabor filtered images


    Contributors:
    Rizki, M.M. (author) / Tamburino, L.A. (author) / Zmuda, M.A. (author)


    Publication date :

    1993-01-01


    Size :

    697756 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Feature Extraction and Analysis of Handwritten Words in Gray-scale Images using Gabor Filters

    Buse, R. / Liu, Z.-Q. / IEEE; Signal Processing Society | British Library Conference Proceedings | 1994



    Enhancing Traffic Signs Recognition Systems Through Gabor Feature Extraction Techniques

    Wicaksono, Immawan / Prawira Negara, Mohamad Agung / Asnoer Laagu, Muh et al. | IEEE | 2024



    Gabor Filter Approach to Joint Feature Extraction and Target Recognition

    Feng Zhu, / Xian-Da Zhang, / Ya-Feng Hu, | IEEE | 2009