Zero-Shot Chinese Character Recognition with Stroke-Level Decomposition

TL;DR

This paper introduces a stroke-based Chinese character recognition method that decomposes characters into strokes, enabling effective zero-shot recognition and outperforming existing methods across various character types.

Contribution

The paper presents a novel stroke-level decomposition approach with a matching strategy to address zero-shot recognition in Chinese characters, improving generalization to unseen characters.

Findings

Outperforms existing methods on zero-shot tasks

Effective across handwritten, printed, and scene characters

Generalizes to other languages with stroke-based characters

Abstract

Chinese character recognition has attracted much research interest due to its wide applications. Although it has been studied for many years, some issues in this field have not been completely resolved yet, e.g. the zero-shot problem. Previous character-based and radical-based methods have not fundamentally addressed the zero-shot problem since some characters or radicals in test sets may not appear in training sets under a data-hungry condition. Inspired by the fact that humans can generalize to know how to write characters unseen before if they have learned stroke orders of some characters, we propose a stroke-based method by decomposing each character into a sequence of strokes, which are the most basic units of Chinese characters. However, we observe that there is a one-to-many relationship between stroke sequences and Chinese characters. To tackle this challenge, we employ a matching-based strategy to transform the predicted stroke sequence to a specific character. We evaluate the proposed method on handwritten characters, printed artistic characters, and scene characters. The experimental results validate that the proposed method outperforms existing methods on both character zero-shot and radical zero-shot tasks. Moreover, the proposed method can be easily generalized to other languages whose characters can be decomposed into strokes.