In this paper, we propose a novel approach for text detec- tion in natural images. Both local and global cues are taken into account for localizing text lines in a coarse-to-fine pro- cedure. First, a Fully Convolutional Network (FCN) model is trained to predict the salient map of text regions in a holistic manner. Then, text line hypotheses are estimated by combining the salient map and character components. Fi- nally, another FCN classifier is used to predict the centroid of each character, in order to remove the false hypotheses. The framework is general for handling text in multiple ori- entations, languages and fonts. The proposed method con- sistently achieves the state-of-the-art performance on three text detection benchmarks: MSRA-TD500, ICDAR2015 and ICDAR2013.
@article{arxiv.1604.04018,
title = {Multi-Oriented Text Detection with Fully Convolutional Networks},
author = {Zheng Zhang and Chengquan Zhang and Wei Shen and Cong Yao and Wenyu Liu and Xiang Bai},
journal= {arXiv preprint arXiv:1604.04018},
year = {2016}
}