Improvement of the end-to-end scene text recognition method for ``text-to-speech'' conversion (Q5150103)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 7308339
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Improvement of the end-to-end scene text recognition method for ``text-to-speech'' conversion |
scientific article; zbMATH DE number 7308339 |
Statements
Improvement of the end-to-end scene text recognition method for “text-to-speech” conversion (English)
0 references
9 February 2021
0 references
scene text detection
0 references
text recognition
0 references
fully convolutional network
0 references
optical character recognition
0 references
text-to-speech synthesizer
0 references
visually impaired
0 references
natural scene images
0 references
0 references
0.6744978427886963
0 references
0.657357394695282
0 references
0.6387666463851929
0 references
0.6330620050430298
0 references
0.631182849407196
0 references
