A method for color image segmentation using a competitive learning clustering scheme is examined, and some basic improvements are made. Two important aspects of the color image segmentation problem, namely color space selection and oversegmentation, are discussed in the context of the algorithm, with comments about suitability and effectivenessof choices for various applications. A variety of settings are tested and compared to highlight performance.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Competitive Learning Techniques for Color Image Segmentation


    Contributors:
    Mavrinac, Aaron (author) / Wu, Jonathan (author) / Chen, Xiang (author) / Tepe, Kemal (author)


    Publication date :

    2008-05-01


    Size :

    485839 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Color Image Segmentation Using Graph-Based Semi-Supervised Learning

    Chen, R. / Sun, J. / Xu, Z. | British Library Online Contents | 2011


    Texture Segmentation by Frequency-Sensitive Elliptical Competitive Learning

    De Backer, S. / Scheunders, P. / IEEE | British Library Conference Proceedings | 1999


    Color image segmentation using Laplacian eigenmaps

    Tziakos, I. / Theoharatos, C. / Laskaris, N.A. et al. | British Library Online Contents | 2009


    Texture segmentation by frequency-sensitive elliptical competitive learning

    De Backer, S. / Scheunders, P. | British Library Online Contents | 2001


    Color image segmentation using Hopfield networks

    Campadelli, P. / Medici, D. / Schettini, R. | British Library Online Contents | 1997