3D Face and Ear Recognition based on Partial MARS Map

Tingting Zhang, Zhichun Mu, Yihang Li, Qing Liu, Yi Zhang

2017

Abstract

This paper proposes a 3D face recognition approach based on facial pose estimation, which is robust to large pose variations in the unconstrained scene. Deep learning method is used to facial pose estimation, and the generation of partial MARS (Multimodal fAce and eaR Spherical) map reduces the probability of feature points appearing in the deformed region. Then we extract the features from the depth and texture maps. Finally, the matching scores from two types of maps should be calculated by Bayes decision to generate the final result. In the large pose variations, the recognition rate of the method in this paper is 94.6%. The experimental results show that our approach has superior performance than the existing methods used on the MARS map, and has potential to deal with 3D face recognition in unconstrained scene.

Download


Paper Citation


in Harvard Style

Zhang T., Mu Z., Li Y., Liu Q. and Zhang Y. (2017). 3D Face and Ear Recognition based on Partial MARS Map . In Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-222-6, pages 633-637. DOI: 10.5220/0006244206330637

in Bibtex Style

@conference{icpram17,
author={Tingting Zhang and Zhichun Mu and Yihang Li and Qing Liu and Yi Zhang},
title={3D Face and Ear Recognition based on Partial MARS Map},
booktitle={Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2017},
pages={633-637},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006244206330637},
isbn={978-989-758-222-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - 3D Face and Ear Recognition based on Partial MARS Map
SN - 978-989-758-222-6
AU - Zhang T.
AU - Mu Z.
AU - Li Y.
AU - Liu Q.
AU - Zhang Y.
PY - 2017
SP - 633
EP - 637
DO - 10.5220/0006244206330637