English

Scene Text Recognition With Finer Grid Rectification

Computer Vision and Pattern Recognition 2020-01-28 v1

Abstract

Scene Text Recognition is a challenging problem because of irregular styles and various distortions. This paper proposed an end-to-end trainable model consists of a finer rectification module and a bidirectional attentional recognition network(Firbarn). The rectification module adopts finer grid to rectify the distorted input image and the bidirectional decoder contains only one decoding layer instead of two separated one. Firbarn can be trained in a weak supervised way, only requiring the scene text images and the corresponding word labels. With the flexible rectification and the novel bidirectional decoder, the results of extensive evaluation on the standard benchmarks show Firbarn outperforms previous works, especially on irregular datasets.

Keywords

Cite

@article{arxiv.2001.09389,
  title  = {Scene Text Recognition With Finer Grid Rectification},
  author = {Gang Wang},
  journal= {arXiv preprint arXiv:2001.09389},
  year   = {2020}
}

Comments

6pages,3 figures

R2 v1 2026-06-23T13:20:45.086Z