Statistical inference and medical image segmentation

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

    Abstract

    Image segmentation can be roughly presented as the grouping of individual image pixels into (meaningful/useful) partition of regions or objects. It is an important area common to a number of research fields such as image processing, computer vision and machine learning. Although a number of algorithms and approaches have been proposed, automated image segmentation continues to be a tantalizing and challenging problem. In this paper, we look at image segmentation as an inference problem and describe the Statistical Region Merging technique (Nock et al; 2004). We will further apply the technique in the segmentation of CT images.
    Original languageEnglish
    Title of host publicationProceedings of the 49th ANZIAM Conference Newcastle, New South Wales 3–7 February 2013
    EditorsDavid Allingham, Roslyn Hickson, Bishnu Lamichhane, Mike Meylan
    Place of PublicationNewcastle, NSW
    PublisherAustralian Mathematical Society Australian and New Zealand Industrial and Applied Mathematics
    Pages73-74
    Number of pages2
    ISBN (Print)978-0-9873276-1-1
    Publication statusPublished - 3 Feb 2013
    EventANZIAM Conference 2013 - Newcastle, Australia
    Duration: 3 Feb 20137 Feb 2013
    Conference number: 49th

    Conference

    ConferenceANZIAM Conference 2013
    CountryAustralia
    CityNewcastle
    Period3/02/137/02/13

    Fingerprint Dive into the research topics of 'Statistical inference and medical image segmentation'. Together they form a unique fingerprint.

    Cite this