# KuroNet: Pre-Modern Japanese Kuzushiji Character Recognition with Deep Learning

arXiv: https://arxiv.org/abs/1910.09433 · HTML: https://mlsanity.com/paper/1910.09433/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Oct 2019.

## Built on by (most cited first, 13 of 13)

- [The LAM Dataset: A Novel Benchmark for Line-Level Handwritten Text Recognition](https://mlsanity.com/paper/2208.07682/) (2022)
- [Boosting Modern and Historical Handwritten Text Recognition with Deformable Convolutions](https://mlsanity.com/paper/2208.08109/) (2022)
- [How to Choose Pretrained Handwriting Recognition Models for Single Writer Fine-Tuning](https://mlsanity.com/paper/2305.02593/) (2023)
- [Restoring and Mining the Records of the Joseon Dynasty via Neural Language Modeling and Machine Translation](https://mlsanity.com/paper/2104.05964/) (2021)
- [Digitization of Document and Information Extraction using OCR](https://mlsanity.com/paper/2506.11156/) (2025)
- [Quo Vadis Handwritten Text Generation for Handwritten Text Recognition?](https://mlsanity.com/paper/2508.09936/) (2025)
- [DKDS: A Benchmark Dataset of Degraded Kuzushiji Documents with Seals for Detection and Binarization](https://mlsanity.com/paper/2511.09117/) (2025)
- [Review of Computational Epigraphy](https://mlsanity.com/paper/2406.06570/) (2024)
- [Multi-Modal Multi-Granularity Tokenizer for Chu Bamboo Slip Scripts](https://mlsanity.com/paper/2409.01011/) (2024)
- [A Text Recognition Dataset from Sahidic Coptic Ancient Manuscripts](https://mlsanity.com/paper/2606.15987/) (2026)
- [Predicting the Ordering of Characters in Japanese Historical Documents](https://mlsanity.com/paper/2106.06786/) (2021)
- [A Multi-Stage Framework for Kuzushiji Character Recognition in Japanese Historical Documents](https://mlsanity.com/paper/2602.19086/) (2026)
- [Impact of Iterative Fine-Tuning on Transcription Accuracy in Complex Historical Sanskrit Manuscripts](https://mlsanity.com/paper/2608.18696/) (2026)

## Abstract (arXiv)

Kuzushiji, a cursive writing style, had been used in Japan for over a thousand years starting from the 8th century. Over 3 millions books on a diverse array of topics, such as literature, science, mathematics and even cooking are preserved. However, following a change to the Japanese writing system in 1900, Kuzushiji has not been included in regular school curricula. Therefore, most Japanese natives nowadays cannot read books written or printed just 150 years ago. Museums and libraries have invested a great deal of effort into creating digital copies of these historical documents as a safeguard against fires, earthquakes and tsunamis. The result has been datasets with hundreds of millions of photographs of historical documents which can only be read by a small number of specially trained experts. Thus there has been a great deal of interest in using Machine Learning to automatically recognize these historical texts and transcribe them into modern Japanese characters. Nevertheless, several challenges in Kuzushiji recognition have made the performance of existing systems extremely poor. To tackle these challenges, we propose KuroNet, a new end-to-end model which jointly recognizes an entire page of text by using a residual U-Net architecture which predicts the location and identity of all characters given a page of text (without any pre-processing). This allows the model to handle long range context, large vocabularies, and non-standardized character layouts. We demonstrate that our system is able to successfully recognize a large fraction of pre-modern Japanese documents, but also explore areas where our system is limited and suggest directions for future work.