This paper presents an end-to-end trainable fast scene text detector, named TextBoxes, which detects scene text with both high accuracy and efficiency in a single network forward pass, involving no post-process except for a standard non-maximum suppression. TextBoxes outperforms competing methods in terms of text localization accuracy and is much faster, taking only 0.09s per image in a fast implementation. Furthermore, combined with a text recognizer, TextBoxes significantly outperforms state-of-the-art approaches on word spotting and end-to-end text recognition tasks.
@article{arxiv.1611.06779,
title = {TextBoxes: A Fast Text Detector with a Single Deep Neural Network},
author = {Minghui Liao and Baoguang Shi and Xiang Bai and Xinggang Wang and Wenyu Liu},
journal= {arXiv preprint arXiv:1611.06779},
year = {2016}
}