Comparison of Appearance-Based and Geometry-Based Bubble Detectors

Nataliya Strokina, Roman Juranek, Tuomas Eerola, Lasse Lensu, Pavel Zemcik, Heikki Kalviainen

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

    2 Citations (Scopus)

    Abstract

    Bubble detection is a complicated tasks since varying lighting conditions changes considerably the appearance of bubbles in liquid. The two common techniques to detect circular objects such as bubbles, the geometry-based and appearance-based approaches, have their advantages and weaknesses. The geometry-based methods often fail to detect small blob-like bubbles that do not match the used geometrical model, and appearance-based approaches are vulnerable to appearance changes caused by, e.g., illumination. In this paper, we compare a geometry-based concentric circular arrangements (CCA) and appearance-based sliding window methods as well as their combinations in terms of bubble detection, gas volume computation, and size distribution estimation. The best bubble detection performance was achieved with the sliding window method whereas the most precise volume estimate was produced by the CCA method. The combination of the two approaches gave only a minor advantage compared to the base methods.

    Translated title of the contributionComparison of Appearance-Based and Geometry-based Bubble Detectors
    Original languageEnglish
    Title of host publicationComputer Vision and Graphics International Conference Computer Vision and Graphigs, ICCVG 2014, Warsaw, Poland, September 15-17,2014
    EditorsLJ Chmielewski, R Kozera, BS Shin, K Wojciechowski
    Place of PublicationBERLIN
    PublisherSpringer-Verlag Berlin Heidelberg
    Pages610-617
    Number of pages8
    ISBN (Print)978-3-319-11330-2
    DOIs
    Publication statusPublished - 2014
    Publication typeA4 Article in a conference publication
    EventInternational Conference Computer Vision and Graphigs -
    Duration: 1 Jan 2014 → …

    Publication series

    NameLecture Notes in Computer Science
    PublisherSpringer
    Volume8671
    ISSN (Print)0302-9743

    Conference

    ConferenceInternational Conference Computer Vision and Graphigs
    Period1/01/14 → …

    Publication forum classification

    • Publication forum level 1

    Fingerprint

    Dive into the research topics of 'Comparison of Appearance-Based and Geometry-Based Bubble Detectors'. Together they form a unique fingerprint.

    Cite this