Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study

TL;DR

This paper provides a comprehensive benchmark for Chinese text recognition, including dataset collection, evaluation standards, baseline evaluations, and insights into the challenges and improvements for Chinese text recognition methods.

Contribution

It introduces standardized datasets and evaluation protocols for Chinese text recognition and evaluates baseline methods, highlighting challenges and potential improvements.

Findings

Baseline performance on Chinese datasets is lower than on English datasets.

Radical-level supervision improves recognition accuracy.

Unified benchmarks facilitate fair comparison of methods.

Abstract

The flourishing blossom of deep learning has witnessed the rapid development of text recognition in recent years. However, the existing text recognition methods are mainly proposed for English texts. As another widely-spoken language, Chinese text recognition (CTR) in all ways has extensive application markets. Based on our observations, we attribute the scarce attention on CTR to the lack of reasonable dataset construction standards, unified evaluation protocols, and results of the existing baselines. To fill this gap, we manually collect CTR datasets from publicly available competitions, projects, and papers. According to application scenarios, we divide the collected datasets into four categories including scene, web, document, and handwriting datasets. Besides, we standardize the evaluation protocols in CTR. With unified evaluation protocols, we evaluate a series of representative text recognition methods on the collected datasets to provide baselines. The experimental results indicate that the performance of baselines on CTR datasets is not as good as that on English datasets due to the characteristics of Chinese texts that are quite different from the Latin alphabet. Moreover, we observe that by introducing radical-level supervision as an auxiliary task, the performance of baselines can be further boosted. The code and datasets are made publicly available at https://github.com/FudanVI/benchmarking-chinese-text-recognition