Conference item icon

Conference item

Deep structured output learning for unconstrained text recognition

Abstract:

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 model, taking the whole word image as a single input. The unaries of the CRF are provided by a CNN that predicts characters at each position of the output, while higher order terms are provided by ano...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Department of Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Department of Engineering Science
Role:
Author
Publisher:
International Conference on Learning Representations
Host title:
International Conference on Learning Representations (ICLR)
Journal:
International Conference on Learning Representations More from this journal
Pages:
1-10
Publication date:
2015-05-09
Acceptance date:
2014-12-19
Event location:
San Diego
Keywords:
Pubs id:
pubs:678958
UUID:
uuid:542ce865-628c-43b5-b308-595bcb5b7a06
Local pid:
pubs:678958
Source identifiers:
678958
Deposit date:
2017-02-09

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP