Synthetic data and artificial neural networks for natural scene text recognition
In this work we present a framework for the recognition of natural scene text. Our framework does not require any human-labelled data, and performs word recognition on the whole image holistically, departing from the character based recognition systems of the past. The deep neural network models at...
Main Authors: | Jaderberg, M, Simonyan, K, Vedaldi, A, Zisserman, A |
---|---|
Formato: | Internet publication |
Idioma: | English |
Publicado: |
arXiv
2014
|
Títulos similares
-
Synthetic data and artificial neural networks for natural scene text recognition
por: Jaderberg, M, et al.
Publicado: (2014) -
Reading text in the wild with convolutional neural networks
por: Jaderberg, M, et al.
Publicado: (2014) -
Reading text in the wild with convolutional neural networks
por: Jaderberg, M, et al.
Publicado: (2015) -
Deep structured output learning for unconstrained text recognition
por: Jaderberg, M, et al.
Publicado: (2014) -
Deep structured output learning for unconstrained text recognition
por: Jaderberg, M, et al.
Publicado: (2015)