A Lightweight CNN for Large-scale Chinese Character Recognition

The ancient Chinese characters appear in various historical documents and poetry. People tend to use optical character recognition tools to understand these uncommon characters. The current Chinese text recognition interface is restricted to a limited character set, such as GB2312-80 and GB18010-2005 standard. However, the newest HanYu Dictionary contains over 55K characters, much more than the commonly-used character set. This work proposes a compact deep network (HYD-CNet) composed of depthwise separable convolutional blocks and co-ordinate attention mechanism to recognize the ancient Chinese characters. It can achieve efficient retrieval and low-storage need for large-scale character recognition on mobile devices. We build a Chinese character database (HYDDB) using the HanYu Dictionary to evaluate the model performance, containing 55,360 character images. The experiment demonstrates that the proposed HYD-CNet has fewer model parameters at a similar accuracy to mainstream lightweight CNNs.

I. Introduction

The ancient Chinese characters that appeared in historical documents have a large amount. Nowadays, people have a high interest in reading ancient literature. However, they are usually unfamiliar with complex Chinese characters and tend to understand them by optical character recognition (OCR) tools and professional dictionaries. The current OCR tools only support commonly-used Chinese characters. Looking up ancient Chinese characters by the dictionary is time-consuming. Moreover, the large-scale character recognition program can be applied in digital libraries and retrieval systems. So OCR tools must support rarely-used characters that appeared in ancient documents.