PARTS-BASED FACE DETECTION AT MULTIPLE VIEWS

Andreas Savakis, David Higgs

2007

Abstract

This paper presents a parts-based approach to face detection, that is intuitive, easy to implement and can be used in conjunction with other image understanding operations that use prominent facial features. Artificial neural networks are trained as view-specific parts detectors for the eyes, mouth and nose. Once these salient facial features are identified, results for each view are integrated through a Bayesian network in order to reach the final decision. System performance is comparable to other state-of the art face detection methods while providing support for different view angles and robustness to partial occlusions.

Paper Citation

in Harvard Style

Savakis A. and Higgs D. (2007). PARTS-BASED FACE DETECTION AT MULTIPLE VIEWS . In Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, ISBN 978-972-8865-74-0, pages 298-301. DOI: 10.5220/0002062202980301

in Bibtex Style

@conference{visapp07,
author={Andreas Savakis and David Higgs},
title={PARTS-BASED FACE DETECTION AT MULTIPLE VIEWS},
booktitle={Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,},
year={2007},
pages={298-301},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002062202980301},
isbn={978-972-8865-74-0},
}

in EndNote Style

TY - CONF
JO - Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,
TI - PARTS-BASED FACE DETECTION AT MULTIPLE VIEWS
SN - 978-972-8865-74-0
AU - Savakis A.
AU - Higgs D.
PY - 2007
SP - 298
EP - 301
DO - 10.5220/0002062202980301