A Feasible Framework for Arbitrary-Shaped Scene Text Recognition
This addresses the challenge of multi-lingual and curved text recognition in real-world scenes, which is an incremental improvement over existing scene text recognition methods.
The paper tackles the problem of recognizing arbitrary-shaped text in scene images by proposing a framework combining instance segmentation for detection and a language model-based attention mechanism for recognition, achieving championship results on the ICDAR2019 Robust Reading Challenge for Latin-only and Latin-Chinese tasks.
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.