Symmetry-Constrained Rectification Network for Scene Text Recognition

Mingkun Yang, Yushuo Guan, Minghui Liao, Xin He, Kaigui Bian, Song Bai, Cong Yao, Xiang Bai; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 9147-9156

Abstract


Reading text in the wild is a very challenging task due to the diversity of text instances and the complexity of natural scenes. Recently, the community has paid increasing attention to the problem of recognizing text instances with irregular shapes. One intuitive and effective way to handle this problem is to rectify irregular text to a canonical form before recognition. However, these methods might struggle when dealing with highly curved or distorted text instances. To tackle this issue, we propose in this paper a Symmetry-constrained Rectification Network (ScRN) based on local attributes of text instances, such as center line, scale and orientation. Such constraints with an accurate description of text shape enable ScRN to generate better rectification results than existing methods and thus lead to higher recognition accuracy. Our method achieves state-of-the-art performance on text with both regular and irregular shapes. Specifically, the system outperforms existing algorithms by a large margin on datasets that contain quite a proportion of irregular text instances, e.g., ICDAR 2015, SVT-Perspective and CUTE80.

Related Material


[pdf]
[bibtex]
@InProceedings{Yang_2019_ICCV,
author = {Yang, Mingkun and Guan, Yushuo and Liao, Minghui and He, Xin and Bian, Kaigui and Bai, Song and Yao, Cong and Bai, Xiang},
title = {Symmetry-Constrained Rectification Network for Scene Text Recognition},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}