Other formats:
BibTeX
LaTeX
RIS
@inproceedings{1809738, author = {Novotný, Vít and Seidlová, Kristýna and Vrabcová, Tereza and Horák, Aleš}, address = {Brno}, booktitle = {Recent Advances in Slavonic Natural Language Processing (RASLAN 2021)}, editor = {Horák, Rychlý, Rambousek}, keywords = {Optical character recognition · Layout analysis; Language identification; Image super-resolution; Medieval texts}, howpublished = {tištěná verze "print"}, language = {eng}, location = {Brno}, isbn = {978-80-263-1670-1}, pages = {29-39}, publisher = {Tribun EU}, title = {When Tesseract Brings Friends: Layout Analysis, Language Identification, and Super-Resolution in the Optical Character Recognition of Medieval Texts}, url = {https://nlp.fi.muni.cz/raslan/raslan21.pdf#page=37}, year = {2021} }
TY - JOUR ID - 1809738 AU - Novotný, Vít - Seidlová, Kristýna - Vrabcová, Tereza - Horák, Aleš PY - 2021 TI - When Tesseract Brings Friends: Layout Analysis, Language Identification, and Super-Resolution in the Optical Character Recognition of Medieval Texts PB - Tribun EU CY - Brno SN - 9788026316701 KW - Optical character recognition · Layout analysis KW - Language identification KW - Image super-resolution KW - Medieval texts UR - https://nlp.fi.muni.cz/raslan/raslan21.pdf#page=37 N2 - The aim of the AHISTO project is to make documents from the Hussite era (1419–1436) available to the general public through a web-hosted searchable database. Although scanned images of letterpress reprints from the 19th and 20th century are available, accurate optical character recognition (OCR) algorithms are required to extract searchable text from the scanned images. In our previous article [15], we have shown that the Tesseract 4 OCR algorithm was the second fastest and the most accurate among five different OCR algorithms. In this article, we investigate the impact of six preprocessing techniques on the accuracy of Tesseract 4. Additionally, we compare Tesseract 4 with three other OCR algorithms on the language identification task. Furthermore, we publish an open dataset [16] of scanned images and OCR texts with human annotations for layout analysis, OCR evaluation, and language identification. In Section 2, we describe the related work in OCR preprocessing. In Section 3, we describe our three preprocessing techniques and our two evaluation tasks. In Section 4, we discuss the results of our evaluation. In Section 5, we offer concluding remarks and ideas for future work in the OCR of medieval texts. ER -
NOVOTNÝ, Vít, Kristýna SEIDLOVÁ, Tereza VRABCOVÁ and Aleš HORÁK. When Tesseract Brings Friends: Layout Analysis, Language Identification, and Super-Resolution in the Optical Character Recognition of Medieval Texts. In Horák, Rychlý, Rambousek. \textit{Recent Advances in Slavonic Natural Language Processing (RASLAN 2021)}. Brno: Tribun EU, 2021, p.~29-39. ISBN~978-80-263-1670-1.
|