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...
| 主要な著者: | , , , |
|---|---|
| フォーマット: | Internet publication |
| 言語: | English |
| 出版事項: |
2014
|