Explainable Connectionist-Temporal-Classification-Based Scene Text Recognition

Connectionist temporal classification (CTC) is a favored decoder in scene text recognition (STR) for its simplicity and efficiency. However, most CTC-based methods utilize one-dimensional (1D) vector sequences, usually derived from a recurrent neural network (RNN) encoder. This results in the absenc...

Descripción completa

Detalles Bibliográficos
Autores principales: Buoy, Rina, Iwamura, Masakazu, Srun, Sovila, Kise, Koichi
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10672533/
https://www.ncbi.nlm.nih.gov/pubmed/37998095
http://dx.doi.org/10.3390/jimaging9110248

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10672533/
https://www.ncbi.nlm.nih.gov/pubmed/37998095
http://dx.doi.org/10.3390/jimaging9110248

Ejemplares similares