TextTubes for Detecting Curved Text in the Wild
This addresses the challenge of accurately detecting curved text in natural images for applications like document analysis and scene understanding, representing an incremental improvement over existing methods.
The paper tackles the problem of detecting curved text in natural images by modeling text instances as tubes around their medial axes and using a parametrization-invariant loss function, achieving state-of-the-art results with an over 8 percentage point improvement in F-score on the CTW-1500 benchmark.
We present a detector for curved text in natural images. We model scene text instances as tubes around their medial axes and introduce a parametrization-invariant loss function. We train a two-stage curved text detector, and evaluate it on the curved text benchmarks CTW-1500 and Total-Text. Our approach achieves state-of-the-art results or improves upon them, notably for CTW-1500 by over 8 percentage points in F-score.