Dealing with Overfitting in the Context of Liveness Detection Using FeatherNets with RGB Images

Miguel Leão, Nuno Gonçalves, Nuno Gonçalves

2023

Abstract

With the increased use of machine learning for liveness detection solutions comes some shortcomings like overfitting, where the model adapts perfectly to the training set, becoming unusable when used with the testing set, defeating the purpose of machine learning. This paper proposes how to approach overfitting without altering the model used by focusing on the input and output information of the model. The input approach focuses on the information obtained from the different modalities present in the datasets used, as well as how varied the information of these datasets is, not only in number of spoof types but as the ambient conditions when the videos were captured. The output approaches were focused on both the loss function, which has an effect on the actual ”learning”, used on the model which is calculated from the model’s output and is then propagated backwards, and the interpretation of said output to define what predictions are considered as bonafide or spoof. Throughout this work, we were able to reduce the overfitting effect with a difference between the best epoch and the average of the last fifty epochs from 36.57% to 3.63%.

Paper Citation

in Harvard Style

Leão M. and Gonçalves N. (2023). Dealing with Overfitting in the Context of Liveness Detection Using FeatherNets with RGB Images. In Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-626-2, pages 62-73. DOI: 10.5220/0011639600003411

in Bibtex Style

@conference{icpram23,
author={Miguel Leão and Nuno Gonçalves},
title={Dealing with Overfitting in the Context of Liveness Detection Using FeatherNets with RGB Images},
booktitle={Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2023},
pages={62-73},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011639600003411},
isbn={978-989-758-626-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Dealing with Overfitting in the Context of Liveness Detection Using FeatherNets with RGB Images
SN - 978-989-758-626-2
AU - Leão M.
AU - Gonçalves N.
PY - 2023
SP - 62
EP - 73
DO - 10.5220/0011639600003411