Spectral Pattern Recognition by a Two-Layer Perceptron: Effects of Training Set Size

    Publication: Working/Discussion PaperWU Working Paper


    Pattern recognition in urban areas is one of the most challenging issues in
    classifying satellite remote sensing data. Parametric pixel-by-pixel classification
    algorithms tend to perform poorly in this context. This is because urban areas
    comprise a complex spatial assemblage of disparate land cover types - including
    built structures, numerous vegetation types, bare soil and water bodies. Thus,
    there is a need for more powerful spectral pattern recognition techniques,
    utilizing pixel-by-pixel spectral information as the basis for automated urban
    land cover detection. This paper adopts the multi-layer perceptron classifier
    suggested and implemented in [5]. The objective of this study is to analyse the
    performance and stability of this classifier - trained and tested for supervised
    classification (8 a priori given land use classes) of a Landsat-5 TM image
    (270 x 360 pixels) from the city of Vienna and its northern surroundings
    - along with varying the training data set in the single-training-site case.
    The performance is measured in terms of total classification, map user's and
    map producer's accuracies. In addition, the stability with initial parameter
    conditions, classification error matrices, and error curves are analysed in some
    detail. (authors' abstract)
    Original languageEnglish
    Place of PublicationVienna
    PublisherWU Vienna University of Economics and Business
    Publication statusPublished - 1 Oct 1996

    Publication series

    NameDiscussion Papers of the Institute for Economic Geography and GIScience

    WU Working Paper Series

    • Discussion Papers of the Institute for Economic Geography and GIScience

    Cite this