Joint recognition of text and layout in historical Russian documents
In this paper, we evaluated the Document Attention Network (DAN), the first end-to-end segmentation-free architecture on Historical Russian Documents. The DAN model jointly recognizes both text and layout from whole documents, it takes whole documents from any size as an input and output the text as...
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Artigo |
| Lingua: | Inglês |
| Pubblicazione: |
ITMO University
2024-12-01
|
| Serie: | Научно-технический вестник информационных технологий, механики и оптики |
| Soggetti: | |
| Accesso online: | https://ntv.elpub.ru/jour/article/view/30 |
| Tags: |
Nessun Tag, puoi essere il primo ad aggiungerne!!
|