Face Blending Data Augmentation for Enhancing Deep Classification

Emna Ghorbel, Ghada Maddouri, Faouzi Ghorbel

2024

Abstract

Facial image classification plays a vital role in computer vision applications, particularly in face recognition. Convolutional Neural Networks have excelled in this domain, however, their performance decline when dealing with small facial datasets. In that context, data augmentation methods have been proposed. In line with this, we introduce the Face Blending data augmentation method, which augments intra-class variability while preserving image semantics. By interpolating faces, we generate non-linear deformations, resulting in in-between images that maintain the original’s global aspect. Results show that Face Blending significantly enhances facial classification. Comparisons with Mix-up and Random Erasing techniques reveal improved accuracy, precision, recall, and F1 score, particularly with limited datasets. This method offers promise for realistic applications contributing to more reliable and accurate facial classification systems with limited data.

Paper Citation

in Harvard Style

Ghorbel E., Maddouri G. and Ghorbel F. (2024). Face Blending Data Augmentation for Enhancing Deep Classification. In Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM; ISBN 978-989-758-684-2, SciTePress, pages 274-280. DOI: 10.5220/0012357900003654

in Bibtex Style

@conference{icpram24,
author={Emna Ghorbel and Ghada Maddouri and Faouzi Ghorbel},
title={Face Blending Data Augmentation for Enhancing Deep Classification},
booktitle={Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM},
year={2024},
pages={274-280},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012357900003654},
isbn={978-989-758-684-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM
TI - Face Blending Data Augmentation for Enhancing Deep Classification
SN - 978-989-758-684-2
AU - Ghorbel E.
AU - Maddouri G.
AU - Ghorbel F.
PY - 2024
SP - 274
EP - 280
DO - 10.5220/0012357900003654
PB - SciTePress