Scale-Residual Learning Network for Scene Text Detection

Detecting incidentally captured text in the wild remains an open problem due to challenging factors including unconstrained scenarios and large scale variation. In this paper, we establish a large-scale scene text detection dataset (LS-Text), containing 36, 000 images and 270, 783 text instances wit...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on circuits and systems for video technology 2021-07, Vol.31 (7), p.2725-2738
Main Authors: Cai, Yuanqiang, Liu, Chang, Cheng, Peirui, Du, Dawei, Zhang, Libo, Wang, Weiqiang, Ye, Qixiang
Format: Article
Language:English
Subjects:
Benchmark testing
Cameras
Datasets
Feature extraction
Feature maps
Image segmentation
Learning
LS-Text dataset
Optimization
scale-residual learning
Source code
Stacking
Task analysis
Text detection
Transforms
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Detecting incidentally captured text in the wild remains an open problem due to challenging factors including unconstrained scenarios and large scale variation. In this paper, we establish a large-scale scene text detection dataset (LS-Text), containing 36, 000 images and 270, 783 text instances with various scales and complex scenarios, to promote the research of text detection. We propose a Scale-residual Learning Network (SLN) to deal with the scale variation problem in a progressive optimization manner. Specifically, we integrate both learnable feature concatenation and feature up-sampling operator. It can effectively eliminate the residuals between the outputs of SLN and ground-truth text instances by processing both the Feature Fusion Residuals (FFR) and the Scale Transformation Residuals (STR), simultaneously. By stacking multi-scale feature maps in a deep-to-shallow manner, SLN continuously optimizes feature representation by accumulating strong semantic information and rich texture details in a scale-residual learning way. Extensive experimental results on five challenging datasets demonstrate the state-of-the-art performance of the proposed SLN model, and the challenging aspects related to real-world scenarios of the proposed LS-Text dataset. Both the source code of SLN and the LS-Text dataset are available at https://github.com/SLN-Text-Detection .
ISSN:1051-8215
1558-2205
DOI:10.1109/TCSVT.2020.3029167