Unsupervised image segmentation with neural networks

Th.H. Gieling, H.J.J. Janssen, H.C. de Vries, P. Loef

    Research output: Chapter in Book/Report/Conference proceedingConference paperAcademic

    1 Citation (Scopus)


    The segmentation of colour images (RGB), distinguishing clusters of image points, representing for example background, leaves and flowers, is performed in a multi-dimensional environment. Considering a two dimensional environment, clusters can be divided by lines. In a three dimensional environment by planes and in an n-dimensional environment by n-1 dimensional structures. Starting with a complete data set the first neural network, represents an n-1 dimensional structure to divide the data set into two subsets. Each subset is once more divided by an additional neural network: recursive partitioning. This results in a tree structure with a neural network in each branching point. Partitioning stops as soon as a partitioning criterium cannot be fulfilled. After the unsupervised training the neural system can be used for the segmentation of images.
    Original languageEnglish
    Title of host publicationProceedings of the Third International Symposium on Sensors in Horticulture, ISHS - Sensors in Horticulture, Tiberias (IL), August 1997
    Publication statusPublished - 2001

    Publication series

    NameActa Horticulturae
    ISSN (Print)0567-7572


    Dive into the research topics of 'Unsupervised image segmentation with neural networks'. Together they form a unique fingerprint.

    Cite this