Cargando…
Generative adversarial network based adaptive data augmentation for handwritten Arabic text recognition
Training deep learning based handwritten text recognition systems needs a lot of data in terms of text images and their corresponding annotations. One way to deal with this issue is to use data augmentation techniques to increase the amount of training data. Generative Adversarial Networks (GANs) ba...
Autores principales: | Eltay, Mohamed, Zidouri, Abdelmalek, Ahmad, Irfan, Elarian, Yousef |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
PeerJ Inc.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8802770/ https://www.ncbi.nlm.nih.gov/pubmed/35174276 http://dx.doi.org/10.7717/peerj-cs.861 |
Ejemplares similares
-
Writer verification of partially damaged handwritten Arabic documents based on individual character shapes
por: Khan, Majid A., et al.
Publicado: (2022) -
Full depth CNN classifier for handwritten and license plate characters recognition
por: Salemdeeb, Mohammed, et al.
Publicado: (2021) -
Reconstructed SqueezeNext with C-CBAM for offline handwritten Chinese character recognition
por: Wu, Ruiqi, et al.
Publicado: (2023) -
Syntactic- and morphology-based text augmentation framework for Arabic sentiment analysis
por: Duwairi, Rehab, et al.
Publicado: (2021) -
S-Swin Transformer: simplified Swin Transformer model for offline handwritten Chinese character recognition
por: Dan, Yongping, et al.
Publicado: (2022)