Building a 3-D Appearance Model of the Human Face

Karl Skoglund, Rasmus Larsen, Brian Lading

AbstractThis paper describes a method for building an appearance
model from three-dimensional data of human faces. The data
consists of 3-D vertices, polygons and a texture map. The method
uses a set of nine manually placed landmarks to automatically form
a dense correspondence of thousands of points. This makes sure the
model is able to capture the subtle details of a face. The model
can be used for face segmentation and fully automated face
registration.
KeywordsAppearance modelling, Face modelling, PCA, VTK
TypeConference paper [Without referee]
ConferenceDSAGM
Year2003    Month August
PublisherDIKU (Datalogisk Institut)
Address
Electronic version(s)[pdf]
BibTeX data [bibtex]
IMM Group(s)Image Analysis & Computer Graphics