@InProceedings{LarocaSanEstLuzMen:2022:FiLoDa,
author = "Laroca, Rayson and Santos, Marcelo and Estevam, Valter and Luz,
Eduardo and Menotti, David",
affiliation = "{Federal University of Paran{\'a}} and {Federal University of
Paran{\'a}} and {Federal University of Paran{\'a}} and {Federal
University of Ouro Preto} and {Federal University of
Paran{\'a}}",
title = "A First Look at Dataset Bias in License Plate Recognition",
booktitle = "Proceedings...",
year = "2022",
organization = "Conference on Graphics, Patterns and Images, 35. (SIBGRAPI)",
keywords = "license plate recognition, dataset bias.",
abstract = "Public datasets have played a key role in advancing the state of
the art in License Plate Recognition (LPR). Although dataset bias
has been recognized as a severe problem in the computer vision
community, it has been largely overlooked in the LPR literature.
LPR models are usually trained and evaluated separately on each
dataset. In this scenario, they have often proven robust in the
dataset they were trained in but showed limited performance in
unseen ones. Therefore, this work investigates the dataset bias
problem in the LPR context. We performed experiments on eight
datasets, four collected in Brazil and four in mainland China, and
observed that each dataset has a unique, identifiable
{"}signature{"} since a lightweight classification model predicts
the source dataset of a license plate (LP) image with more than
95% accuracy. In our discussion, we draw attention to the fact
that most LPR models are probably exploiting such signatures to
improve the results achieved in each dataset at the cost of losing
generalization capability. These results emphasize the importance
of evaluating LPR models in cross-dataset setups, as they provide
a better indication of generalization (hence real-world
performance) than within-dataset ones.",
conference-location = "Natal, RN",
conference-year = "24-27 Oct. 2022",
doi = "10.1109/SIBGRAPI55357.2022.9991768",
url = "http://dx.doi.org/10.1109/SIBGRAPI55357.2022.9991768",
language = "en",
ibi = "8JMKD3MGPEW34M/47M827H",
url = "http://urlib.net/ibi/8JMKD3MGPEW34M/47M827H",
targetfile = "laroca2022first-inpe.pdf",
urlaccessdate = "2024, Apr. 29"
}