Handwriting recognition in historical documents using very large vocabularies

© ACM 2013. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in HIP '13 Proceedings of the 2nd International Workshop on Historical Document Imaging and Processinghttp://dx.doi.org/10.1145/2501115.2501116Language models are used in automatic transcription system to resolve ambiguities. This is done by limiting the vocabulary of words that can be recognized as well as estimating the n-gram probability of the words in the given text. In the context of historical documents, a non-unified spelling and the limited amount of written text pose a substantial problem for the selection of the recognizable vocabulary as well as the computation of the word probabilities. In this paper we propose for the transcription of historical Spanish text to keep the corpus for the n-gram limited to a sample of the target text, but expand the vocabulary with words gathered from external resources. We analyze the performance of such a transcription system with different sizes of external vocabularies and demonstrate the applicability and the significant increase in recognition accuracy of using up to 300 thousand external words.This work has been supported by the European project FP7-PEOPLE-2008-IAPP: 230653 the European Research Council’s Advanced Grant ERC-2010-AdG 20100407, the Spanish R&D projects TIN2009-14633-C03-03, RYC-2009-05031, TIN2011-24631, TIN2012-37475-C02-02, MITTRAL (TIN2009-14633-C03-01), Active2Trans (TIN2012-31723) as well as the Swiss National Science Foundation fellowship project PBBEP2_141453.Frinken, V.; Fischer, A.; Martínez-Hinarejos, C. (2013). Handwriting recognition in historical documents using very large vocabularies. ACM. https://doi.org/10.1145/2501115.250111