loading
Papers

Research.Publish.Connect.

Paper

Authors: Marcin Kopaczka ; Philipp Gräbel and Dorit Merhof

Affiliation: Institute of Imaging and Computer Vision, RWTH Aachen University, Aachen and Germany

ISBN: 978-989-758-319-3

Keyword(s): Active Appearance Models, Occlusion, Robust Cost Functions, Feature Descriptors.

Abstract: Active Appearance Models (AAM) are a well-established method for facial landmark detection and face tracking. Due to their widespread use, several additions to the original AAM algorithms have been proposed in recent years. Two previously proposed improvements that address different shortcomings are using robust statistics for occlusion handling and adding feature descriptors for improved landmark fitting performance. In this paper, we show that a combination of both methods is possible and provide a feasible and effective way to improve robustness and precision of the AAM fitting process. We describe how robust cost functions can be incorporated into the feature-based fitting procedure and evaluate our approach. We apply our method to the challenging 300-videos-in-the-wild dataset and show that our approach allows robust face tracking even under severe occlusions.

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 100.24.122.228

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Kopaczka, M.; Gräbel, P. and Merhof, D. (2018). Robust Statistics for Feature-based Active Appearance Models.In Proceedings of the 15th International Joint Conference on e-Business and Telecommunications - Volume 2: ICETE, ISBN 978-989-758-319-3, pages 421-426. DOI: 10.5220/0006910005870592

@conference{icete18,
author={Marcin Kopaczka. and Philipp Gräbel. and Dorit Merhof.},
title={Robust Statistics for Feature-based Active Appearance Models},
booktitle={Proceedings of the 15th International Joint Conference on e-Business and Telecommunications - Volume 2: ICETE,},
year={2018},
pages={421-426},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006910005870592},
isbn={978-989-758-319-3},
}

TY - CONF

JO - Proceedings of the 15th International Joint Conference on e-Business and Telecommunications - Volume 2: ICETE,
TI - Robust Statistics for Feature-based Active Appearance Models
SN - 978-989-758-319-3
AU - Kopaczka, M.
AU - Gräbel, P.
AU - Merhof, D.
PY - 2018
SP - 421
EP - 426
DO - 10.5220/0006910005870592

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.