# Offline Handwritten Chinese Text Recognition with Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2006.15619 · HTML: https://mlsanity.com/paper/2006.15619/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jun 2020.

## Built on by (most cited first, 5 of 5)

- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [How to Use Dropout Correctly on Residual Networks with Batch Normalization](https://mlsanity.com/paper/2302.06112/) (2023)
- [Qianfan-VL: Domain-Enhanced Universal Vision-Language Models](https://mlsanity.com/paper/2509.18189/) (2025)
- [AiM: Taking Answers in Mind to Correct Chinese Cloze Tests in Educational Applications](https://mlsanity.com/paper/2208.12505/) (2022)
- [Understanding Cross-Language Transfer Improvements in Low-Resource HTR: The Role of Sequence Modeling](https://mlsanity.com/paper/2605.05900/) (2026)

## Abstract (arXiv)

Deep learning based methods have been dominating the text recognition tasks in different and multilingual scenarios. The offline handwritten Chinese text recognition (HCTR) is one of the most challenging tasks because it involves thousands of characters, variant writing styles and complex data collection process. Recently, the recurrent-free architectures for text recognition appears to be competitive as its highly parallelism and comparable results. In this paper, we build the models using only the convolutional neural networks and use CTC as the loss function. To reduce the overfitting, we apply dropout after each max-pooling layer and with extreme high rate on the last one before the linear layer. The CASIA-HWDB database is selected to tune and evaluate the proposed models. With the existing text samples as templates, we randomly choose isolated character samples to synthesis more text samples for training. We finally achieve 6.81% character error rate (CER) on the ICDAR 2013 competition set, which is the best published result without language model correction.