@inbook{a4e2820fa88744b0948021c6c0a7a9c6,
title = "Can one deep learning model learn script-independent multilingual word-spotting?",
abstract = "Word spotting has gained increased attention lately as it can be used to extract textual information from handwritten documents and scene-text images. Current word spotting approaches are designed to work on a single language and/or script. Building intelligent models that learn script-independent multilingual word-spotting is challenging due to the large variability of multilingual alphabets and symbols. We used ResNet-152 and the Pyramidal Histogram of Characters (PHOC) embedding to build a one-model script-independent multilingual word-spotting and we tested it on Latin, Arabic, and Bangla (Indian) languages. The one-model we propose performs on par with the multi-model language-specific word-spotting system, and thus, reduces the number of models needed for each script and/or language.",
keywords = "Handwriting, Histogram of Characters, Multitasking, PHOC, ResNet, Scene text images",
author = "Mohammed Al-Rawi and Ernest Valveny and Dimosthenis Karatzas",
note = "Funding Information: This work has received funding from from the European Union's Horizon 2020 research and innovation programme under the Marie Skodowska-Curie grant agreement No 665919, research grants TIN2017-89779-P and 2017-SGR-1783 from the Spanish and Catalan government, respectively. Publisher Copyright: {\textcopyright} 2019 IEEE.",
year = "2019",
month = sep,
doi = "10.1109/ICDAR.2019.00050",
language = "English",
series = "Proceedings of the International Conference on Document Analysis and Recognition, ICDAR",
pages = "260--267",
booktitle = "Proceedings - 15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019",
}