Multi-oriented Text Detection with Fully Convolutional Networks
Citations Over TimeTop 1% of 2016 papers
Abstract
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.
Related Papers
- → Calculating Centroids in Constrained Mixture Experiments(1983)26 cited
- Keeping Conflicts Latent: "Salient" versus "Non-Salient" Interpersonal Conflict Management Strategies of Japanese(2013)
- → Design of Multi-Grade Centroid Adjusting Mechanism for Simulation Inspection Device(2013)
- New method of centroid detection in wavefront aberration measurement of human eye(2002)
- First moment spot centroid detection with a threshold to compute the centroid(2015)