Wedgelet Enhanced Appearance Models

Sune Darkner, Rasmus Larsen, Mikkel Bille Stegmann, Bjarne Kjær Ersbøll

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

    100 Downloads (Pure)

    Abstract

    Statistical region-based segmentation methods such as the Active Appearance Model (AAM) are used for establishing dense correspondences in images based on learning the variation in shape and pixel intensities in a training set. For low resolution 2D images correspondences can be recovered reliably in real-time. However, as resolution increases this becomes infeasible due to excessive storage and computational requirements. In this paper we propose to reduce the textural components by modelling the coefficients of a wedgelet based regression tree instead of the original pixel intensities. The wedgelet regression trees employed are based on triangular domains and estimated using cross validation. The wedgelet regression trees are functional descriptions of the intensity information and serve to 1) reduce noise and 2) produce a compact textural description. The wedgelet enhanced appearance model is applied to a case study of human faces. Compression rates of the texture information of 1:40 is obtained without sacrificing segmentation accuracy noticably, even at compression rates of 1:150 fair segmentation is achieved.
    Original languageEnglish
    Title of host publication2nd International Workshop on Generative Model Based Vision (GMBV 2004), Washington, D. C., July, 2nd
    PublisherIEEE
    Publication date2004
    Publication statusPublished - 2004
    Event2nd International Workshop on Generative Model Based Vision - washington, D.C.
    Duration: 1 Jan 2004 → …
    Conference number: 2

    Conference

    Conference2nd International Workshop on Generative Model Based Vision
    Number2
    Citywashington, D.C.
    Period01/01/2004 → …

    Cite this

    Darkner, S., Larsen, R., Stegmann, M. B., & Ersbøll, B. K. (2004). Wedgelet Enhanced Appearance Models. In 2nd International Workshop on Generative Model Based Vision (GMBV 2004), Washington, D. C., July, 2nd IEEE. http://www.imm.dtu.dk/pubdb/p.php?3134