Deep structured output learning for unconstrained text recognition
We develop a representation suitable for the unconstrained recognition of words in natural images, where unconstrained means that there is no fixed lexicon and words have unknown length. To this end we propose a convolutional neural network (CNN) based architecture which incorporates a Conditional R...
| Main Authors: | , , , |
|---|---|
| Format: | Internet publication |
| Language: | English |
| Published: |
arXiv
2014
|