Wedgelet Enhanced Appearance Models

AbstractStatistical 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.
Keywordsappearance model, wedgelet, image segmentation, quadtree,
TypeConference paper [With referee]
Conference2nd International Workshop on Generative Model Based Vision (GMBV 2004), Washington, D. C., July, 2nd
EditorsArthur Pece, Rasmus Larsen, and Alan Yuille
Year2004    Month July
AddressNew Jersey, US
Electronic version(s)[pdf]
BibTeX data [bibtex]
IMM Group(s)Image Analysis & Computer Graphics