A Robust Dot-focused Classification Approach to Convolutional Braille Recognition
JUCS - Journal of Universal Computer Science · 28.04.2026 · 32 (4) · 486-518
DOI: 10.3897/jucs.161636 ↗Kurz gefasst
Fachartikel in der Zeitschrift JUCS - Journal of Universal Computer Science, online erschienen am 28.04.2026. Verfasst von Wicus J. van der Linden und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The effect of imbalanced data on the optical character recognition of Braille text is investigated by applying two techniques to a set of convolutional neural network image classification models. A multilabel classification framework is applied to identify the combination of Braille dots present in a character sample. This approach is compared to the multiclass classification framework prevalent in the literature, which directly identifies each sample as one of 64 possible Braille characters. Furthermore, data resampling methods are applied to investigate the impact of class imbalance on the multilabel and multiclass modelling approaches, respectively. The multilabel models are shown to achieve statistically significantly better performance than multiclass models, across different data resampling strategies. This includes better generalisation to out of distribution testing data from different Braille language codes, as well as robust performance under experimental image augmentation conditions. Furthermore, while multiclass models achieve better performance when trained on resampled data compared to training without resampling, this performance increase fails to rival the performance of the multilabel classification models across metrics and resampling strategies.
Zitieren
APA
Linden, W. J. V. D., Grobler, T. L., & Zijl, L. V. (2026). A Robust Dot-focused Classification Approach to Convolutional Braille Recognition. JUCS - Journal of Universal Computer Science, 32(4), 486-518. https://doi.org/10.3897/jucs.161636
Vancouver
Linden WJVD, Grobler TL, Zijl LV. A Robust Dot-focused Classification Approach to Convolutional Braille Recognition. JUCS - Journal of Universal Computer Science. 2026;32(4):486-518. doi:10.3897/jucs.161636
BibTeX
@article{Linden2026,
author = {Linden, Wicus J. van der and Grobler, Trienko L. and Zijl, Lynette van},
title = {A Robust Dot-focused Classification Approach to Convolutional Braille Recognition},
journal = {JUCS - Journal of Universal Computer Science},
year = {2026},
volume = {32},
number = {4},
pages = {486--518},
doi = {10.3897/jucs.161636}
}
EUVIMED