Unsupervised Facial Biometric Data Filtering for Age and Gender Estimation

Krešimir Bešenić, Jörgen Ahlberg, Igor S. Pandžić

2019

Abstract

Availability of large training datasets was essential for the recent advancement and success of deep learning methods. Due to the difficulties related to biometric data collection, datasets with age and gender annotations are scarce and usually limited in terms of size and sample diversity. Web-scraping approaches for automatic data collection can produce large amounts weakly labeled noisy data. The unsupervised facial biometric data filtering method presented in this paper greatly reduces label noise levels in web-scraped facial biometric data. Experiments on two large state-of-the-art web-scraped facial datasets demonstrate the effectiveness of the proposed method, with respect to training and validation scores, training convergence, and generalization capabilities of trained age and gender estimators.

Paper Citation

in Harvard Style

Bešenić K., Ahlberg J. and Pandžić I. (2019). Unsupervised Facial Biometric Data Filtering for Age and Gender Estimation. In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP; ISBN 978-989-758-354-4, SciTePress, pages 209-217. DOI: 10.5220/0007257202090217

in Bibtex Style

@conference{visapp19,
author={Krešimir Bešenić and Jörgen Ahlberg and Igor S. Pandžić},
title={Unsupervised Facial Biometric Data Filtering for Age and Gender Estimation},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP},
year={2019},
pages={209-217},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007257202090217},
isbn={978-989-758-354-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP
TI - Unsupervised Facial Biometric Data Filtering for Age and Gender Estimation
SN - 978-989-758-354-4
AU - Bešenić K.
AU - Ahlberg J.
AU - Pandžić I.
PY - 2019
SP - 209
EP - 217
DO - 10.5220/0007257202090217
PB - SciTePress