Chinese Character Recognition with Radical-Structured Stroke Trees

TL;DR

This paper introduces a radical-structured stroke tree representation for Chinese character recognition, leveraging hierarchical radical and stroke information to improve robustness against distribution shifts like blurring and occlusion.

Contribution

It proposes a novel two-stage decomposition framework and a radical-structured stroke tree encoding to enhance recognition accuracy under challenging conditions.

Findings

Outperforms state-of-the-art methods in distribution shift scenarios

Demonstrates robustness against blurring, occlusion, and zero-shot challenges

Achieves higher accuracy with radical-structured stroke trees

Abstract

The flourishing blossom of deep learning has witnessed the rapid development of Chinese character recognition. However, it remains a great challenge that the characters for testing may have different distributions from those of the training dataset. Existing methods based on a single-level representation (character-level, radical-level, or stroke-level) may be either too sensitive to distribution changes (e.g., induced by blurring, occlusion, and zero-shot problems) or too tolerant to one-to-many ambiguities. In this paper, we represent each Chinese character as a stroke tree, which is organized according to its radical structures, to fully exploit the merits of both radical and stroke levels in a decent way. We propose a two-stage decomposition framework, where a Feature-to-Radical Decoder perceives radical structures and radical regions, and a Radical-to-Stroke Decoder further predicts the stroke sequences according to the features of radical regions. The generated radical structures and stroke sequences are encoded as a Radical-Structured Stroke Tree (RSST), which is fed to a Tree-to-Character Translator based on the proposed Weighted Edit Distance to match the closest candidate character in the RSST lexicon. Our extensive experimental results demonstrate that the proposed method outperforms the state-of-the-art single-level methods by increasing margins as the distribution difference becomes more severe in the blurring, occlusion, and zero-shot scenarios, which indeed validates the robustness of the proposed method.