Další formáty:
BibTeX
LaTeX
RIS
@inproceedings{1809720, author = {Bankovič, Mikuláš and Novotný, Vít and Sojka, Petr}, address = {Brno}, booktitle = {Recent Advances in Slavonic Natural Language Processing (RASLAN 2021)}, editor = {Horák, Rychlý, Rambousek}, keywords = {Super-resolution; Optical character recognition; Medieval texts}, howpublished = {tištěná verze "print"}, language = {eng}, location = {Brno}, isbn = {978-80-263-1670-1}, pages = {11-18}, publisher = {Tribun EU}, title = {Application of Super-Resolution Models in Optical Character Recognition of Czech Medieval Texts}, url = {https://raslan2021.nlp-consulting.net/}, year = {2021} }
TY - JOUR ID - 1809720 AU - Bankovič, Mikuláš - Novotný, Vít - Sojka, Petr PY - 2021 TI - Application of Super-Resolution Models in Optical Character Recognition of Czech Medieval Texts PB - Tribun EU CY - Brno SN - 9788026316701 KW - Super-resolution KW - Optical character recognition KW - Medieval texts UR - https://raslan2021.nlp-consulting.net/ N2 - Optical character recognition (OCR) of scanned images is used in multiple applications in numerous domains and several frameworks and OCR algorithms are publicly available. However, some domains such as medieval texts suffer from low accuracy, mainly due to low resources and poor quality data. For such domains, preprocessing techniques help to increase the accuracy of OCR algorithms. In this paper, we experiment with two super-resolution models: Waifu2x and SRGAN. We use the models to reduce noise and increase the image resolution of scanned medieval texts. We evaluate the models on the AHISTO project dataset and compare them against several baselines. We show that our models produce improvements in OCR accuracy. ER -
BANKOVIČ, Mikuláš, Vít NOVOTNÝ a Petr SOJKA. Application of Super-Resolution Models in Optical Character Recognition of Czech Medieval Texts. In Horák, Rychlý, Rambousek. \textit{Recent Advances in Slavonic Natural Language Processing (RASLAN 2021)}. Brno: Tribun EU, 2021, s.~11-18. ISBN~978-80-263-1670-1.
|