# Online and Offline Handwritten Chinese Character Recognition: A Comprehensive Study and New Benchmark

arXiv: https://arxiv.org/abs/1606.05763 · HTML: https://mlsanity.com/paper/1606.05763/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jun 2016.

## Built on by (most cited first, 17 of 17)

- [Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study](https://mlsanity.com/paper/2112.15093/) (2021)
- [Zero-Shot Chinese Character Recognition with Stroke-Level Decomposition](https://mlsanity.com/paper/2106.11613/) (2021)
- [A Survey of Historical Document Image Datasets](https://mlsanity.com/paper/2203.08504/) (2022)
- [RZCR: Zero-shot Character Recognition via Radical-based Reasoning](https://mlsanity.com/paper/2207.05842/) (2022)
- [Chinese Character Recognition with Radical-Structured Stroke Trees](https://mlsanity.com/paper/2211.13518/) (2022)
- [Toward Zero-shot Character Recognition: A Gold Standard Dataset with Radical-level Annotations](https://mlsanity.com/paper/2308.00655/) (2023)
- [STAR: Zero-Shot Chinese Character Recognition with Stroke- and Radical-Level Decompositions](https://mlsanity.com/paper/2210.08490/) (2022)
- [Stroke-Based Autoencoders: Self-Supervised Learners for Efficient Zero-Shot Chinese Character Recognition](https://mlsanity.com/paper/2207.08191/) (2022)
- [MegaHan97K: A Large-Scale Dataset for Mega-Category Chinese Character Recognition with over 97K Categories](https://mlsanity.com/paper/2506.04807/) (2025)
- [Writer adaptation for offline text recognition: An exploration of neural network-based methods](https://mlsanity.com/paper/2307.15071/) (2023)
- [Restoring Ancient Ideograph: A Multimodal Multitask Neural Network Approach](https://mlsanity.com/paper/2403.06682/) (2024)
- [Zero-Shot Chinese Character Recognition with Hierarchical Multi-Granularity Image-Text Aligning](https://mlsanity.com/paper/2505.24837/) (2025)
- [Sentence-level Online Handwritten Chinese Character Recognition](https://mlsanity.com/paper/2108.02561/) (2021)
- [Kurdish Handwritten Character Recognition using Deep Learning Techniques](https://mlsanity.com/paper/2210.13734/) (2022)
- [Kanji Workbook: A Writing-Based Intelligent Tutoring System for Learning Proper Japanese Kanji Writing Technique with Instructor-Emulated Assessment](https://mlsanity.com/paper/2504.13888/) (2025)
- [Entropy-Aware Structural Alignment for Zero-Shot Handwritten Chinese Character Recognition](https://mlsanity.com/paper/2602.03913/) (2026)
- [Logographic Character Visual Pretraining via Semantic-based Contrastive Learning](https://mlsanity.com/paper/2608.00096/) (2026)

## Abstract (arXiv)

Recent deep learning based methods have achieved the state-of-the-art performance for handwritten Chinese character recognition (HCCR) by learning discriminative representations directly from raw data. Nevertheless, we believe that the long-and-well investigated domain-specific knowledge should still help to boost the performance of HCCR. By integrating the traditional normalization-cooperated direction-decomposed feature map (directMap) with the deep convolutional neural network (convNet), we are able to obtain new highest accuracies for both online and offline HCCR on the ICDAR-2013 competition database. With this new framework, we can eliminate the needs for data augmentation and model ensemble, which are widely used in other systems to achieve their best results. This makes our framework to be efficient and effective for both training and testing. Furthermore, although directMap+convNet can achieve the best results and surpass human-level performance, we show that writer adaptation in this case is still effective. A new adaptation layer is proposed to reduce the mismatch between training and test data on a particular source layer. The adaptation process can be efficiently and effectively implemented in an unsupervised manner. By adding the adaptation layer into the pre-trained convNet, it can adapt to the new handwriting styles of particular writers, and the recognition accuracy can be further improved consistently and significantly. This paper gives an overview and comparison of recent deep learning based approaches for HCCR, and also sets new benchmarks for both online and offline HCCR.