A scene text detector for text with arbitrary shapes

DOI10.1155/2020/8916028MaRDI QIDQ778692zbMATH OpenOpenAlexFDO

Authors Weijia Wu, Jici Xing, Cheng Yang, Yuxing Wang, Hong Zhou

Publication date 3 July 2020

Published in Mathematical Problems in Engineering (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1155/2020/8916028

Mathematics Subject Classification ID

Detection theory in information and communication theory (94A13)

Review text

Summary: The performance of text detection is crucial for the subsequent recognition task. Currently, the accuracy of the text detector still needs further improvement, particularly those with irregular shapes in a complex environment. We propose a pixel-wise method based on instance segmentation for scene text detection. Specifically, a text instance is split into five components: a Text Skeleton and four Directional Pixel Regions, then restoring itself based on these elements and receiving supplementary information from other areas when one fails. Besides, a Confidence Scoring Mechanism is designed to filter characters similar to text instances. Experiments on several challenging benchmarks demonstrate that our method achieves state-of-the-art results in scene text detection with an F-measure of 84.6\% on Total-Text and 86.3\% on CTW1500.

Recommendations

• Bottom-up scene text detection with Markov clustering networks
• A learning-based method to detect and segment text from scene images
• Feature fusion-based text information mining method for natural scenes
• Improvement of the end-to-end scene text recognition method for ``text-to-speech conversion
• scientific article; zbMATH DE number 1930939

Cites work

• Scene Text Recognition in Mobile Applications by Character Descriptor and Structure Configuration
• Text String Detection From Natural Scenes by Structure-Based Partition and Grouping
• TextBoxes++: A Single-Shot Oriented Scene Text Detector
• TextField: Learning a Deep Direction Field for Irregular Scene Text Detection

Cited in

(5)

• Bottom-up scene text detection with Markov clustering networks
• A learning-based method to detect and segment text from scene images
• Scene Text Recognition in Mobile Applications by Character Descriptor and Structure Configuration
• Improvement of the end-to-end scene text recognition method for ``text-to-speech conversion
• Feature fusion-based text information mining method for natural scenes

This page was built for publication: A scene text detector for text with arbitrary shapes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q778692)