@inproceedings{4302abd69c5c4092bc29367507176fd5,
title = "The influence of language orthographic characteristics on digital word recognition",
abstract = "We study the effect of language orthographic characteristics on the performance of digital word recognition in degraded documents such as historical documents. We provide a rigorous scheme for quantifying the influence of the orthographic characteristics on the quality of word recognition in such documents. We study and compare several orthographic characteristics for four natural languages and measure the effect of each individual characteristic on the digital word recognition process. To this end we create synthetic languages, for which all characteristics, except the one we examine, are identical, and measure the performance of two word recognition algorithms on synthetic documents of these languages. We examine and summarize the influence of the values of each characteristic on the performance of these word recognition methods.",
keywords = "Degraded documents, Natural language characteristics, Orthographic neighborhood, Word recognition",
author = "Ofer Biller and Jihad El-Sana and Klara Kedem",
year = "2014",
month = jan,
day = "1",
doi = "10.1109/DAS.2014.35",
language = "English",
isbn = "9781479932436",
series = "Proceedings - 11th IAPR International Workshop on Document Analysis Systems, DAS 2014",
publisher = "Institute of Electrical and Electronics Engineers",
pages = "131--135",
booktitle = "Proceedings - 11th IAPR International Workshop on Document Analysis Systems, DAS 2014",
address = "United States",
note = "11th IAPR International Workshop on Document Analysis Systems, DAS 2014 ; Conference date: 07-04-2014 Through 10-04-2014",
}