2D-3D Face Recognition via Restricted Boltzmann Machines

Xiaolong Wang, Vincent Ly, Rui Guo, Chandra Kambhamettu

2014

Abstract

This paper proposes a new scheme for the 2D-3D face recognition problem. Our proposed framework mainly consists of Restricted Boltzmann Machines (RBMs) and a correlation learning model. In the framework, a single-layer network based on RBMs is adopted to extract latent features over two different modalities. Furthermore, the latent hidden layer features of different models are projected to formulate a shared space based on correlation learning. Then several different correlation learning schemes are evaluated against the proposed scheme. We evaluate the advocated approach on a popular face dataset-FRGCV2.0. Experimental results demonstrate that the latent features extracted using RBMs are effective in improving the performance of correlation mapping for 2D-3D face recognition.

Download


Paper Citation


in Harvard Style

Wang X., Ly V., Guo R. and Kambhamettu C. (2014). 2D-3D Face Recognition via Restricted Boltzmann Machines . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-004-8, pages 574-580. DOI: 10.5220/0004736505740580

in Bibtex Style

@conference{visapp14,
author={Xiaolong Wang and Vincent Ly and Rui Guo and Chandra Kambhamettu},
title={2D-3D Face Recognition via Restricted Boltzmann Machines},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={574-580},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004736505740580},
isbn={978-989-758-004-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)
TI - 2D-3D Face Recognition via Restricted Boltzmann Machines
SN - 978-989-758-004-8
AU - Wang X.
AU - Ly V.
AU - Guo R.
AU - Kambhamettu C.
PY - 2014
SP - 574
EP - 580
DO - 10.5220/0004736505740580