Deep Residual Text Detection Network for Scene Text

by   Xiangyu Zhu, et al.

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 F-measure of 0.91, which outperforms previous state-of-the-art results in scene text detection.


page 3

page 5


Feature Enhancement Network: A Refined Scene Text Detector

In this paper, we propose a refined scene text detector with a novel Fea...

Fused Text Segmentation Networks for Multi-oriented Scene Text Detection

In this paper, we introduce a novel end-end framework for multi-oriented...

Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection

Recently, transformer-based methods have achieved promising progresses i...

PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection

This paper presents how we can achieve the state-of-the-art accuracy in ...

Accurate Text Localization in Natural Image with Cascaded Convolutional Text Network

We introduce a new top-down pipeline for scene text detection. We propos...

Scene Text Detection with Selected Anchor

Object proposal technique with dense anchoring scheme for scene text det...

Multi-Granularity Prediction for Scene Text Recognition

Scene text recognition (STR) has been an active research topic in comput...