Robust End-to-End Offline Chinese Handwriting Text Page Spotter with Text Kernel

TL;DR

This paper introduces an end-to-end framework for offline Chinese handwriting text recognition that unifies detection and recognition using a text kernel, significantly improving robustness and accuracy.

Contribution

It proposes a novel text kernel that integrates global features, enabling joint detection and recognition, reducing dependency on detection accuracy, and achieving state-of-the-art results.

Findings

Achieved 99.12% line-level recognition accuracy on CASIA-HWDB2.0-2.2

Achieved 94.27% line-level accuracy on ICDAR-2013

Outperformed previous methods in robustness and accuracy

Abstract

Offline Chinese handwriting text recognition is a long-standing research topic in the field of pattern recognition. In previous studies, text detection and recognition are separated, which leads to the fact that text recognition is highly dependent on the detection results. In this paper, we propose a robust end-to-end Chinese text page spotter framework. It unifies text detection and text recognition with text kernel that integrates global text feature information to optimize the recognition from multiple scales, which reduces the dependence of detection and improves the robustness of the system. Our method achieves state-of-the-art results on the CASIA-HWDB2.0-2.2 dataset and ICDAR-2013 competition dataset. Without any language model, the correct rates are 99.12% and 94.27% for line-level recognition, and 99.03% and 94.20% for page-level recognition, respectively.