On the Cross-dataset Generalization in License Plate Recognition

Rayson Laroca, Everton V. Cardoso, Diego R. Lucio, Valter Estevam, Valter Estevam, David Menotti

2022

Abstract

Automatic License Plate Recognition (ALPR) systems have shown remarkable performance on license plates (LPs) from multiple regions due to advances in deep learning and the increasing availability of datasets. The evaluation of deep ALPR systems is usually done within each dataset; therefore, it is questionable if such results are a reliable indicator of generalization ability. In this paper, we propose a traditional-split versus leave-one-dataset-out experimental setup to empirically assess the cross-dataset generalization of 12 Optical Character Recognition (OCR) models applied to LP recognition on 9 publicly available datasets with a great variety in several aspects (e.g., acquisition settings, image resolution, and LP layouts). We also introduce a public dataset for end-to-end ALPR that is the first to contain images of vehicles with Mercosur LPs and the one with the highest number of motorcycle images. The experimental results shed light on the limitations of the traditional-split protocol for evaluating approaches in the ALPR context, as there are significant drops in performance for most datasets when training and testing the models in a leave-one-dataset-out fashion.

Paper Citation

in Harvard Style

Laroca R., Cardoso E., Lucio D., Estevam V. and Menotti D. (2022). On the Cross-dataset Generalization in License Plate Recognition. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP; ISBN 978-989-758-555-5, SciTePress, pages 166-178. DOI: 10.5220/0010846800003124

in Bibtex Style

@conference{visapp22,
author={Rayson Laroca and Everton V. Cardoso and Diego R. Lucio and Valter Estevam and David Menotti},
title={On the Cross-dataset Generalization in License Plate Recognition},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP},
year={2022},
pages={166-178},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010846800003124},
isbn={978-989-758-555-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP
TI - On the Cross-dataset Generalization in License Plate Recognition
SN - 978-989-758-555-5
AU - Laroca R.
AU - Cardoso E.
AU - Lucio D.
AU - Estevam V.
AU - Menotti D.
PY - 2022
SP - 166
EP - 178
DO - 10.5220/0010846800003124
PB - SciTePress