Attention-Based Fully Gated CNN-BGRU for Russian Handwritten Text

This article considers the task of handwritten text recognition using attention-based encoder–decoder networks trained in the Kazakh and Russian languages. We have developed a novel deep neural network model based on a fully gated CNN, supported by multiple bidirectional gated recurrent unit (BGRU)...

Descripción completa

Detalles Bibliográficos
Autores principales: Abdallah, Abdelrahman, Hamada, Mohamed, Nurseitov, Daniyar
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8321198/
https://www.ncbi.nlm.nih.gov/pubmed/34460538
http://dx.doi.org/10.3390/jimaging6120141

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8321198/
https://www.ncbi.nlm.nih.gov/pubmed/34460538
http://dx.doi.org/10.3390/jimaging6120141

Ejemplares similares