3D REGISTRATION AND MODELLING FOR FACE RECOGNITION

Li Bai, Yi Song

2006

Abstract

AbstractThis paper presents a new approach to automatic 3D face recognition using a model-based approach. This work uses real 3D dense point cloud data acquired with a stereo face scanner. Since the point clouds are in varied orientations, by applying a non-iterative registration technique, we automatically transform each point cloud to a canonical position and detect facial features used for defining the frontal part of face which is to be modelled in next step. Unlike the iterative ICP algorithm, our non-iterative registration process is scale invariant. An efficient B-spline surface-fitting technique is developed to represent 3D faces in a way that allows efficient surface comparison. This is based on a novel knot vector standardisation algorithm to allow one-to-one mapping from the object space to a parameter space. Consequently, correspondence between objects is established based on shape descriptors, which can be used for recognition.

Paper Citation

in Harvard Style

Bai L. and Song Y. (2006). 3D REGISTRATION AND MODELLING FOR FACE RECOGNITION . In Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, ISBN 972-8865-40-6, pages 201-208. DOI: 10.5220/0001371002010208

in Bibtex Style

@conference{visapp06,
author={Li Bai and Yi Song},
title={3D REGISTRATION AND MODELLING FOR FACE RECOGNITION},
booktitle={Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,},
year={2006},
pages={201-208},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001371002010208},
isbn={972-8865-40-6},
}

in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,
TI - 3D REGISTRATION AND MODELLING FOR FACE RECOGNITION
SN - 972-8865-40-6
AU - Bai L.
AU - Song Y.
PY - 2006
SP - 201
EP - 208
DO - 10.5220/0001371002010208