Deep Residual Text Detection Network for Scene Text

Scene text detection is a challenging problem in computer vision. In this paper, we propose a novel text detection network based on prevalent object detection frameworks. In order to obtain stronger semantic feature, we adopt ResNet as feature extraction layers and exploit multi-level feature by combining hierarchical convolutional networks. A vertical proposal mechanism is utilized to avoid proposal classification, while regression layer remains working to improve localization accuracy. Our approach evaluated on ICDAR2013 dataset achieves 0.91 F-measure, which outperforms previous state-of-the-art results in scene text detection.

I. Introduction

Text detection is an important part of text content analysis, especially for reading natural text in the wild. Scene text detection is becoming increasing attractive to researchers, with the development of smart phone and tremendous demands of text recognition in Augmentation Reality (AR). Unlike traditional documental text, detecting scene text seems to be a much more challenging task due to illuminations, perspective distortion and complex background.