A Feasible Framework for Arbitrary-Shaped Scene Text Recognition

Jinjin Zhang; Wei Wang; Di Huang; Qingjie Liu; Yunhong Wang

A Feasible Framework for Arbitrary-Shaped Scene Text Recognition

Computer Vision and Pattern Recognition 2019-12-13 v2

Authors: Jinjin Zhang , Wei Wang , Di Huang , Qingjie Liu , Yunhong Wang

Abstract

Deep learning based methods have achieved surprising progress in Scene Text Recognition (STR), one of classic problems in computer vision. In this paper, we propose a feasible framework for multi-lingual arbitrary-shaped STR, including instance segmentation based text detection and language model based attention mechanism for text recognition. Our STR algorithm not only recognizes Latin and Non-Latin characters, but also supports arbitrary-shaped text recognition. Our method wins the championship on Scene Text Spotting Task (Latin Only, Latin and Chinese) of ICDAR2019 Robust Reading Challenge on ArbitraryShaped Text Competition. Code is available at https://github.com/zhang0jhon/AttentionOCR.

Keywords

scene text detection and recognition handwritten character recognition text classification

Cite

@article{arxiv.1912.04561,
  title  = {A Feasible Framework for Arbitrary-Shaped Scene Text Recognition},
  author = {Jinjin Zhang and Wei Wang and Di Huang and Qingjie Liu and Yunhong Wang},
  journal= {arXiv preprint arXiv:1912.04561},
  year   = {2019}
}

A Feasible Framework for Arbitrary-Shaped Scene Text Recognition

Abstract

Keywords

Cite

Related papers