Institutul de Matematică şi Informatică "Vladimir Andrunachievici"
Universitatea de Stat din MoldovaRO EN
Distinctive features of recognition for documents printed in the Romanian transitional alphabets
Authors: Bumbu Tudor, Burţeva Liudmila, Cojocaru Svetlana, Colesnicov Alexandru, Malahov Ludmila
Keywords: cultural heritage, OCR, Romanian transitional alphabets
– 1.32 Mb
Keywords: cultural heritage, OCR, Romanian transitional alphabets
Abstract
In this paper, we summarize the research of digitization of documents printed by Romanian transitional alphabet. These printings are the most original Romanian historical documents, which makes our experience useful when researching OCR methods for similar alphabets. The current work is focused to OCR that is the first stage of scanned documents digitization. The technique of OCR of documents, printed in the Romanian transitional alphabet, is presented. In particular, this technique is embedded in our digitization platform HeDy. A series of examples is presented to demonstrate the application of the described technique.Tudor Bumbu 1;2, Lyudmila Burtseva1;3,
Svetlana Cojocaru1;4,
Alexandru Colesnicov1;5, Ludmila Malahov1;6,
1“V. Andrunachievici” Institute of Mathematics and Computer Science, Chisinau, Republic
of Moldova
2ORCID: https://orcid.org/0000-0001-5311-4464
E-mail:
3ORCID: https://orcid.org/0000-0002-9064-2538
E-mail:
4ORCID: https://orcid.org/0009-0003-1025-5306
E-mail:
5ORCID: https://orcid.org/0000-0002-4383-3753
E-mail:
6ORCID: https://orcid.org/0000-0001-9846-0299
E-mail:
Svetlana Cojocaru1;4,
Alexandru Colesnicov1;5, Ludmila Malahov1;6,
1“V. Andrunachievici” Institute of Mathematics and Computer Science, Chisinau, Republic
of Moldova
2ORCID: https://orcid.org/0000-0001-5311-4464
E-mail:
3ORCID: https://orcid.org/0000-0002-9064-2538
E-mail:
4ORCID: https://orcid.org/0009-0003-1025-5306
E-mail:
5ORCID: https://orcid.org/0000-0002-4383-3753
E-mail:
6ORCID: https://orcid.org/0000-0001-9846-0299
E-mail:
DOI
https://doi.org/10.56415/csjm.v31.17Fulltext
– 1.32 Mb
Contents
- Development of Digital Twins to Support the Functioning of Cyber-physical Systems
- Multilingual Fine-Grained Named Entity Recognition
- Distinctive features of recognition for documents printed in the Romanian transitional alphabets
- Supplementing elearning systems with adaptive content generation elements
- Challenges associated with using AR technology in education
- On some aspects of medical data quality
- On some classes of formulas in $S5$ which are pre-complete relative to existential expressibility
