On Decomposing Object Appearance using PCA and Wavelet bases with Applications to Image Segmentation

Mikkel Bille Stegmann, Søren Forchhammer, Hans Joachim Werner (Editor)

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    67 Downloads (Pure)

    Abstract

    Generative models capable of synthesising complete object images have over the past few years proven their worth when interpreting images. Due to the recent development of computational machinery it has become feasible to model the variation of image intensities and landmark positions over the complete object surface using principal component analysis. This typically involves matrices with a few thousands and up to 100.000+ rows. This paper demonstrates applications of such models applied on colour images of human faces and cardiac magnetic resonance images. Further, we devise methods for alleviating the obvious computational and storage requirements of these large models by means of truncated wavelet bases.
    Original languageEnglish
    Title of host publicationMATRIX'02, Eleventh International Workshop on Matrices and Statistics
    Number of pages21
    PublisherInformatics and Mathematical Modelling, Technical University of Denmark, DTU
    Publication date2002
    Publication statusPublished - 2002
    EventEleventh International Workshop on Matrices and Statistics - Richard Petersens Plads, Building 321, Kgs. Lyngby, Denmark
    Duration: 29 Aug 200231 Aug 2002
    Conference number: 11

    Conference

    ConferenceEleventh International Workshop on Matrices and Statistics
    Number11
    LocationRichard Petersens Plads, Building 321
    Country/TerritoryDenmark
    CityKgs. Lyngby
    Period29/08/200231/08/2002

    Fingerprint

    Dive into the research topics of 'On Decomposing Object Appearance using PCA and Wavelet bases with Applications to Image Segmentation'. Together they form a unique fingerprint.

    Cite this