@InProceedings{MohamedAliSouibgui2022,
author="Mohamed Ali Souibgui
and Ali Furkan Biten
and Sounak Dey
and Alicia Fornes
and Yousri Kessentini
and Lluis Gomez
and Dimosthenis Karatzas
and Josep Llados",
title="One-shot Compositional Data Generation for Low Resource Handwritten Text Recognition",
booktitle="Winter Conference on Applications of Computer Vision",
year="2022",
optkeywords="Document Analysis",
abstract="Low resource Handwritten Text Recognition (HTR) is a hard problem due to the scarce annotated data and the very limited linguistic information (dictionaries and language models). This appears, for example, in the case of historical ciphered manuscripts, which are usually written with invented alphabets to hide the content. Thus, in this paper we address this problem through a data generation technique based on Bayesian Program Learning (BPL). Contrary to traditional generation approaches, which require a huge amount of annotated images, our method is able to generate human-like handwriting using only one sample of each symbol from the desired alphabet. After generating symbols, we create synthetic lines to train state-of-the-art HTR architectures in a segmentation free fashion. Quantitative and qualitative analyses were carried out and confirm the effectiveness of the proposed method, achieving competitive results compared to the usage of real annotated data.",
optnote="DAG; 602.230; 600.140",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=3615), last updated on Thu, 27 Apr 2023 14:51:23 +0200",
doi="10.1109/WACV51458.2022.00262",
opturl="https://ieeexplore.ieee.org/document/9706788",
file=":http://refbase.cvc.uab.es/files/SBD2022.pdf:PDF"
}