Deep structured output learning for unconstrained text recognition

We develop a representation suitable for the unconstrained recognition of words in natural images: the general case of no fixed lexicon and unknown length. To this end we propose a convolutional neural network (CNN) based architecture which incorporates a Conditional Random Field (CRF) graphical mod...

Descripción completa

Detalles Bibliográficos
Autores principales: Jaderberg, M, Simonyan, K, Vedaldi, A, Zisserman, A
Formato: Conference item
Lenguaje:English
Publicado: International Conference on Learning Representations 2015