Deformation Robust Text Spotting with Geometric Prior

TL;DR

This paper introduces a new dataset and a novel method for text spotting that is robust to deformation and font diversity, improving recognition of complex character shapes in natural images.

Contribution

The paper presents ARText, a large dataset with deformed and diverse fonts, and DR TextSpotter, a method using geometric priors and graph convolution for robust text recognition.

Findings

Effective on ARText and IC19-ReCTS datasets

Improves recognition of deformed and diverse fonts

Outperforms existing methods in robustness

Abstract

The goal of text spotting is to perform text detection and recognition in an end-to-end manner. Although the diversity of luminosity and orientation in scene texts has been widely studied, the font diversity and shape variance of the same character are ignored in recent works, since most characters in natural images are rendered in standard fonts. To solve this problem, we present a Chinese Artistic Dataset, termed as ARText, which contains 33,000 artistic images with rich shape deformation and font diversity. Based on this database, we develop a deformation robust text spotting method (DR TextSpotter) to solve the recognition problem of complex deformation of characters in different fonts. Specifically, we propose a geometric prior module to highlight the important features based on the unsupervised landmark detection sub-network. A graph convolution network is further constructed to fuse the character features and landmark features, and then performs semantic reasoning to enhance the discrimination for different characters. The experiments are conducted on ARText and IC19-ReCTS datasets. Our results demonstrate the effectiveness of our proposed method.