MobText: A Compact Method for Scene Text Localization

Luis Gustavo Lorgus Decker, Allan da Silva Pinto, Jose Luis Flores Campana, Manuel Cordova Neira, Andreza A. dos Santos, Jhonatas S. Conceição, Marcus A. Angeloni, Lin Tzy Li, Ricardo da S. Torres

2020

Abstract

Multiple research initiatives have been reported to yield highly effective results for the text detection problem. However, most of those solutions are very costly, which hamper their use in several applications that rely on the use of devices with restrictive processing power, like smartwatches and mobile phones. In this paper, we address this issue by investigating the use of efficient object detection networks for this problem. We propose the combination of two light architectures, MobileNetV2 and Single Shot Detector (SSD), for the text detection problem. Experimental results in the ICDAR’11 and ICDAR’13 datasets demonstrate that our solution yields the best trade-off between effectiveness and efficiency and also achieved the state-of-the-art results in the ICDAR’11 dataset with an f-measure of 96.09%.

Paper Citation

in Harvard Style

Decker L., Pinto A., Campana J., Neira M., Santos A., Conceição J., Angeloni M., Li L. and Torres R. (2020). MobText: A Compact Method for Scene Text Localization. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP; ISBN 978-989-758-402-2, SciTePress, pages 343-350. DOI: 10.5220/0008954103430350

in Bibtex Style

@conference{visapp20,
author={Luis Gustavo Lorgus Decker and Allan da Silva Pinto and Jose Luis Flores Campana and Manuel Cordova Neira and Andreza A. dos Santos and Jhonatas S. Conceição and Marcus A. Angeloni and Lin Tzy Li and Ricardo da S. Torres},
title={MobText: A Compact Method for Scene Text Localization},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP},
year={2020},
pages={343-350},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008954103430350},
isbn={978-989-758-402-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP
TI - MobText: A Compact Method for Scene Text Localization
SN - 978-989-758-402-2
AU - Decker L.
AU - Pinto A.
AU - Campana J.
AU - Neira M.
AU - Santos A.
AU - Conceição J.
AU - Angeloni M.
AU - Li L.
AU - Torres R.
PY - 2020
SP - 343
EP - 350
DO - 10.5220/0008954103430350
PB - SciTePress