Papers › TextCohesion: Detecting Text for Arbitrary Shapes

TextCohesion: Detecting Text for Arbitrary Shapes

22 Apr 2019arXiv:1904.12640archive 2025-07-28

Weijia Wu, Jici Xing, Hong Zhou

In this paper, we propose a pixel-wise method named TextCohesion for scene text detection, which splits a text instance into five key components: a Text Skeleton and four Directional Pixel Regions. These components are easier to handle than the entire text instance. A confidence scoring mechanism is designed to filter characters that are similar to text. Our method can integrate text contexts intensively when backgrounds are complex. Experiments on two curved challenging benchmarks demonstrate that TextCohesion outperforms state-of-the-art methods, achieving the F-measure of 84.6% on Total-Text and bfseries86.3% on SCUT-CTW1500.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Curved Text DetectionScene Text DetectionText Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Curved Text Detection SCUT-CTW1500 TextCohesion F-Measure 86.3% #1 of 5 Archive leaderboard report
Scene Text Detection Total-Text TextCohesion F-Measure 84.6% #16 of 27 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections