Summary: Technical Report BU­CS­TR­2001­021
A shorter version of this paper is published in the proceedings of
IEEE Workshop on Cues in Communication, 2001
3D Hand Pose Estimation by Finding Appearance­Based
Matches in a Large Database of Training Views
Vassilis Athitsos and Stan Sclaroff
Computer Science Department
Boston University
111 Cummington Street
Boston, MA 02215
e­mail fathitsos,sclaroffg@cs.bu.edu
Abstract
Ongoing work towards appearance­based 3D hand pose estimation from a single
image is presented. A large database of synthetic hand views is generated using a 3D
hand model and computer graphics. The views display different hand shapes as seen
from arbitrary viewpoints. Each synthetic view is automatically labeled with param­
eters describing its hand shape and viewing parameters. Given an input image, the
system retrieves the most similar database views, and uses the shape and viewing pa­
rameters of those views as candidate estimates for the parameters of the input image.
Preliminary results are presented, in which appearance­based similarity is defined in

Source: Athitsos, Vassilis - Department of Computer Science and Engineering, University of Texas at Arlington
Boston University, Department of Computer Science

Collections: Computer Technologies and Information Sciences