Margin Guidance Network for Arbitrary-shaped Scene Text Detection

  • Xin Li
  • , Xingjiao Wu
  • , Tianlong Ma*
  • , Zhao Zhou
  • , Luhui Chen
  • , Liang He
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Segmentation-based scene text detection approaches have been adopted to arbitrary-shaped texts and have achieved a great progress. However, false detection always easily exist when the arbitrary-shaped texts are close to each other. In this paper, we propose the Margin Guidance Network (MGN) that mainly based on the margin constraint residual module (MCRM) to address aforementioned problem. The MCRM considers the margins between multiple text instance masks to guide the training of network and improve the performance on text detection. The MCRM contains two prediction branch, the one can generate the multiple different scale of masks for a text instance and the other branch is used to generate multiple margins between the above masks. Experimental results on three public benchmarks including ICDAR2015, CTW1500 and Total-Text have demonstrated that the proposed MGN achieves the state-of-The-Art results.

Original languageEnglish
Title of host publicationProceedings - IEEE 32nd International Conference on Tools with Artificial Intelligence, ICTAI 2020
EditorsMiltos Alamaniotis, Shimei Pan
PublisherIEEE Computer Society
Pages1111-1117
Number of pages7
ISBN (Electronic)9781728192284
DOIs
StatePublished - Nov 2020
Event32nd IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2020 - Virtual, Baltimore, United States
Duration: 9 Nov 202011 Nov 2020

Publication series

NameProceedings - International Conference on Tools with Artificial Intelligence, ICTAI
Volume2020-November
ISSN (Print)1082-3409

Conference

Conference32nd IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2020
Country/TerritoryUnited States
CityVirtual, Baltimore
Period9/11/2011/11/20

Keywords

  • Margin Guidance Network
  • Scene text detection
  • arbitrary-shaped text

Fingerprint

Dive into the research topics of 'Margin Guidance Network for Arbitrary-shaped Scene Text Detection'. Together they form a unique fingerprint.

Cite this