Robust End-to-End Offline Chinese Handwriting Text Page Spotter with Text Kernel
This addresses the challenge of improving robustness in Chinese handwriting recognition for applications like document digitization, though it appears incremental by building on existing detection-recognition integration methods.
The paper tackles the problem of offline Chinese handwriting text recognition by proposing an end-to-end framework that unifies text detection and recognition using a text kernel, achieving state-of-the-art correct rates of up to 99.12% for line-level and 99.03% for page-level recognition on benchmark datasets.
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.