Deep Structured Output Learning for Unconstrained Text Recognition
@article{Jaderberg2015DeepSO, title={Deep Structured Output Learning for Unconstrained Text Recognition}, author={Max Jaderberg and K. Simonyan and A. Vedaldi and Andrew Zisserman}, journal={CoRR}, year={2015}, volume={abs/1412.5903} }
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… CONTINUE READING
Supplemental Presentations
Figures, Tables, and Topics from this paper
Paper Mentions
171 Citations
Sequence to sequence learning for unconstrained scene text recognition
- Computer Science
- ArXiv
- 2016
- 1
- Highly Influenced
- PDF
Convolutional recurrent neural networks with hidden Markov model bootstrap for scene text recognition
- Computer Science
- IET Comput. Vis.
- 2017
- 9
Attention and Language Ensemble for Scene Text Recognition with Convolutional Sequence Modeling
- Computer Science
- ACM Multimedia
- 2018
- 23
- Highly Influenced
Visual Attention Models for Scene Text Recognition
- Computer Science
- 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)
- 2017
- 31
- Highly Influenced
- PDF
LEWIS: Latent Embeddings for Word Images and Their Semantics
- Computer Science
- 2015 IEEE International Conference on Computer Vision (ICCV)
- 2015
- 18
- PDF
Attention-Based Deep Neural Network and Its Application to Scene Text Recognition
- Computer Science
- 2019 IEEE 11th International Conference on Communication Software and Networks (ICCSN)
- 2019
Deep neural network with attention model for scene text recognition
- Computer Science
- IET Comput. Vis.
- 2017
- 5
References
SHOWING 1-10 OF 28 REFERENCES
Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
- Computer Science
- ArXiv
- 2014
- 524
- PDF
Reading Text in the Wild with Convolutional Neural Networks
- Computer Science
- International Journal of Computer Vision
- 2015
- 697
- PDF
End-to-end text recognition with convolutional neural networks
- Computer Science
- Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012)
- 2012
- 713
- Highly Influential
- PDF
Scene Text Recognition using Higher Order Language Priors
- Computer Science
- BMVC
- 2012
- 455
- Highly Influential
- PDF
Supervised mid-level features for word image representation
- Computer Science
- 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2015
- 82
- PDF
Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks
- Computer Science
- ICLR
- 2014
- 499
- Highly Influential
- PDF
Word Spotting and Recognition with Embedded Attributes
- Computer Science, Medicine
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- 2014
- 312
- PDF