A vision system for online wear detection

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

    10 Downloads (Pure)

    Abstract

    Wear detection has traditionally restricted itself to offline study and measurement. In this paper a vision system for online monitoring and detection of wear is described. This system uses a video zoom microscope and a high-resolution monochrome camera to capture the image series of a moving surface under study. An algorithm based on multichannel filtering for the detection of wear patterns is presented. The wear patterns are extracted by filtering the acquired image using a Gabor filter bank with multiple narrow spatial frequency and orientation channels. Experiments show the feasibility and usefulness of the proposed vision system and detection method of wear patterns.
    Original languageEnglish
    Title of host publicationXVII IMEKO World Congress : Metrology in the 3rd millennium
    Subtitle of host publicationBook of summaries: June 22-27, 2003 Dubrovnik, Croatia
    EditorsDamir Ilić, Mladen Boršić, Josip Butorac
    Place of PublicationDubrovnik, Croatia
    PublisherCroatian Metrology Society
    Number of pages5
    ISBN (Electronic)978-953-7124-00-7
    ISBN (Print)978-953-9609-39-7
    Publication statusPublished - 22 Jun 2003
    EventXVII IMEKO World Congress 2003: Metrology in the 3rd Millennium - Dubrovnik, Croatia
    Duration: 22 Jun 200327 Jun 2003
    Conference number: 17

    Conference

    ConferenceXVII IMEKO World Congress 2003
    CountryCroatia
    CityDubrovnik
    Period22/06/0327/06/03

    Fingerprint Dive into the research topics of 'A vision system for online wear detection'. Together they form a unique fingerprint.

    Cite this