On the analysis of neural networks for image processing

B.J. van der Zwaag, Cornelis H. Slump, Lambert Spaanenburg

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    2 Citations (Scopus)
    192 Downloads (Pure)

    Abstract

    This paper illustrates a novel method to analyze artificial neural networks so as to gain insight into their internal functionality. To this purpose, we will show analysis results of some feed-forward–error-back-propagation neural networks for image processing. We will describe them in terms of domain-dependent basic functions, which are, in the case of the digital image processing domain, differential operators of various orders and with various angles of operation. Some other pixel classification techniques are analyzed in the same way, enabling easy comparison.
    Original languageUndefined
    Title of host publicationProceedings of KES2003 vol. II
    EditorsVasile Palade, Robert J. Howlett, Lakhmi Jain
    Place of PublicationOxford, UK
    PublisherSpringer
    Pages950-957
    Number of pages8
    ISBN (Print)3-540-40804-5
    DOIs
    Publication statusPublished - Sept 2003
    EventProceedings of KES2003 vol. II - Oxford, U.K.
    Duration: 3 Sept 20035 Sept 2003

    Publication series

    NameLecture Notes in Computer Science
    PublisherSpringer
    Volume2774

    Conference

    ConferenceProceedings of KES2003 vol. II
    Period3/09/035/09/03
    Other3-5 September 2003

    Keywords

    • IR-45400
    • METIS-212150
    • EWI-9667

    Cite this