Stroke-Based Scene Text Erasing Using Synthetic Data for Training

Research output: Contribution to journalArticlepeer-review

Abstract

Scene text erasing, which replaces text regions with reasonable content in natural images, has drawn significant attention in the computer vision community in recent years. There are two potential subtasks in scene text erasing: text detection and image inpainting. Both subtasks require considerable data to achieve better performance; however, the lack of a large-scale real-world scene-text removal dataset does not allow existing methods to realize their potential. To compensate for the lack of pairwise real-world data, we made considerable use of synthetic text after additional enhancement and subsequently trained our model only on the dataset generated by the improved synthetic text engine. Our proposed network contains a stroke mask prediction module and background inpainting module that can extract the text stroke as a relatively small hole from the cropped text image to maintain more background content for better inpainting results. This model can partially erase text instances in a scene image with a bounding box or work with an existing scene-text detector for automatic scene text erasing. The experimental results from the qualitative and quantitative evaluation on the SCUT-Syn, ICDAR2013, and SCUT-EnsText datasets demonstrate that our method significantly outperforms existing state-of-the-art methods even when they are trained on real-world data.

Original languageEnglish
Pages (from-to)9306-9320
Number of pages15
JournalIEEE Transactions on Image Processing
Volume30
DOIs
Publication statusPublished - 2021

Keywords

  • background inpainting
  • Scene text erasing
  • synthetic text

ASJC Scopus subject areas

  • Software
  • Computer Graphics and Computer-Aided Design

Fingerprint

Dive into the research topics of 'Stroke-Based Scene Text Erasing Using Synthetic Data for Training'. Together they form a unique fingerprint.

Cite this