Multi-oriented Text Detection with Fully Convolutional Networks

In this paper, we propose a novel approach for text detection in natural images. Both local and global cues are taken into account for localizing text lines in a coarse-to-fine procedure. First, a Fully Convolutional Network (FCN) model is trained to predict the salient map of text regions in a holi...

Full description

Saved in:
Bibliographic Details
Published in2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 4159 - 4167
Main Authors Zheng Zhang, Chengquan Zhang, Wei Shen, Cong Yao, Wenyu Liu, Xiang Bai
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2016
Subjects
Benchmark testing
Computer vision
Context
Detectors
Estimation
Labeling
Text recognition
Online AccessGet full text

Cover

More Information
Summary:In this paper, we propose a novel approach for text detection in natural images. Both local and global cues are taken into account for localizing text lines in a coarse-to-fine procedure. 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. Finally, 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 orientations, languages and fonts. The proposed method consistently achieves the state-of-the-art performance on three text detection benchmarks: MSRA-TD500, ICDAR2015 and ICDAR2013.
ISSN:1063-6919
DOI:10.1109/CVPR.2016.451