Towards a Font Classification Model for Romanian Cyrillic Documents
This paper presents a solution on how to classify the fonts in the 17th century Romanian Cyrillic documents. This solution is based on a mix of unsupervised and supervised machine learning technics. The unsupervised process is the application of K-Means method to create the dataset with the fonts ch...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Vladimir Andrunachievici Institute of Mathematics and Computer Science
2021-12-01
|
| Series: | Computer Science Journal of Moldova |
| Subjects: | |
| Online Access: | http://www.math.md/files/csjm/v29-n3/v29-n3-(pp291-298).pdf |
| _version_ | 1818007374403731456 |
|---|---|
| author | Tudor Bumbu |
| author_facet | Tudor Bumbu |
| author_sort | Tudor Bumbu |
| collection | DOAJ |
| description | This paper presents a solution on how to classify the fonts in the 17th century Romanian Cyrillic documents. This solution is based on a mix of unsupervised and supervised machine learning technics. The unsupervised process is the application of K-Means method to create the dataset with the fonts characters and their labels, whilst the supervised process is to train two different architectures of neural networks to classify these characters. |
| first_indexed | 2024-04-14T05:14:42Z |
| format | Article |
| id | doaj.art-92eee104f03d44ef9143515e5ec95b5c |
| institution | Directory Open Access Journal |
| issn | 1561-4042 |
| language | English |
| last_indexed | 2024-04-14T05:14:42Z |
| publishDate | 2021-12-01 |
| publisher | Vladimir Andrunachievici Institute of Mathematics and Computer Science |
| record_format | Article |
| series | Computer Science Journal of Moldova |
| spelling | doaj.art-92eee104f03d44ef9143515e5ec95b5c2022-12-22T02:10:24ZengVladimir Andrunachievici Institute of Mathematics and Computer ScienceComputer Science Journal of Moldova1561-40422021-12-01293(87)291298Towards a Font Classification Model for Romanian Cyrillic DocumentsTudor Bumbu0``Vladimir Andrunachievici'' Institute of Mathematics and Computer Science, 5 Academiei str., MD-2028, Chisinau, Republic of MoldovaThis paper presents a solution on how to classify the fonts in the 17th century Romanian Cyrillic documents. This solution is based on a mix of unsupervised and supervised machine learning technics. The unsupervised process is the application of K-Means method to create the dataset with the fonts characters and their labels, whilst the supervised process is to train two different architectures of neural networks to classify these characters.http://www.math.md/files/csjm/v29-n3/v29-n3-(pp291-298).pdfold documentsocrfont classificationneural networksromanian cyrillic |
| spellingShingle | Tudor Bumbu Towards a Font Classification Model for Romanian Cyrillic Documents Computer Science Journal of Moldova old documents ocr font classification neural networks romanian cyrillic |
| title | Towards a Font Classification Model for Romanian Cyrillic Documents |
| title_full | Towards a Font Classification Model for Romanian Cyrillic Documents |
| title_fullStr | Towards a Font Classification Model for Romanian Cyrillic Documents |
| title_full_unstemmed | Towards a Font Classification Model for Romanian Cyrillic Documents |
| title_short | Towards a Font Classification Model for Romanian Cyrillic Documents |
| title_sort | towards a font classification model for romanian cyrillic documents |
| topic | old documents ocr font classification neural networks romanian cyrillic |
| url | http://www.math.md/files/csjm/v29-n3/v29-n3-(pp291-298).pdf |
| work_keys_str_mv | AT tudorbumbu towardsafontclassificationmodelforromaniancyrillicdocuments |