Existing classification methods which are based on the homogeneous-region mostly involve the best segmentation scale choice. Using the so-called best segmentation scale to respond the subjective defined objects, it would not be the best way for classification. Therefore we propose a simple classification method with high precision. It is a new kind of multi-scale homogeneous-region model, fully uses the longitudinal information which the homogeneous-region model provides, and adopts the scale-span classification method based on decision tree to improve the accuracy, rather than directly carrying on the best scale choice. The experimental result proves the scale-span method is more accurate than sole scale lassification.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    The Scale-Span Classification Research for Multispectral Images Based on the Homogeneous-Region


    Contributors:
    Lin, Liqun (author) / Shu, Ning (author) / Gong, Yan (author) / Xiao, Jun (author)


    Publication date :

    2008-05-01


    Size :

    2590801 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    ATR Applied to Multispectral Images Classification Based on KLT

    Quintiliano, P. / Santa-Rosa, A. | British Library Online Contents | 2003



    Robust Photometric Invariant Region Detection in Multispectral Images

    Gevers, T. / Stokman, H. M. | British Library Online Contents | 2003


    Classification of multispectral images according to crosswise textural characteristics

    Dejesusparada, N. / Doofilho, E. / Mascarenhas, N. D. A. et al. | NTRS | 1980