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 another CNN that detects the presence of N-grams. We show that this entire model (CRF, character predictor, N-gram predictor) can be jointly optimised by back-propagating the structured output loss, essentially requiring the system to perform multi-task learning, and training uses purely synthetically generated data. The resulting model is a more accurate system on standard real-world text recognition benchmarks than character prediction alone, setting a benchmark for systems that have not been trained on a particular lexicon. In addition, our model achieves state-of-the-art accuracy in lexicon-constrained scenarios, without being specifically modelled for constrained recognition. To test the generalisation of our model, we also perform experiments with random alpha-numeric strings to evaluate the method when no visual language model is applicable.
- Publication status:
- Not published
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Preview, Version of record, pdf, 1.7MB, Terms of use)
-
- Publisher copy:
- 10.48550/arXiv.1412.5903
Authors
- Publisher:
- International Conference on Learning Representations
- Pages:
- 1-10
- Publication date:
- 2015-05-09
- Acceptance date:
- 2014-12-19
- Event title:
- 3rd International Conference on Learning Representations (ICLR 2015)
- Event location:
- San Diego, CA, USA
- Event website:
- https://iclr.cc/archive/www/doku.php%3Fid=iclr2015:main.html
- Event start date:
- 2015-05-07
- Event end date:
- 2015-05-09
- DOI:
- Language:
-
English
- Keywords:
- Pubs id:
-
pubs:678958
- UUID:
-
uuid:542ce865-628c-43b5-b308-595bcb5b7a06
- Local pid:
-
pubs:678958
- Source identifiers:
-
678958
- Deposit date:
-
2017-02-09
- ARK identifier:
Terms of use
- Copyright date:
- 2015
- Notes:
- This paper was presented at the 3rd International Conference on Learning Representations (ICLR 2015), 7th-9th May 2015, San Diego, CA, USA.
If you are the owner of this record, you can report an update to it here: Report update to this record