# Fully Convolutional Networks for Handwriting Recognition

arXiv: https://arxiv.org/abs/1907.04888 · HTML: https://mlsanity.com/paper/1907.04888/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jul 2019.

## Built on by (most cited first, 10 of 10)

- [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)
- [Classification of Handwritten Names of Cities and Handwritten Text Recognition using Various Deep Learning Models](https://mlsanity.com/paper/2102.04816/) (2021)
- [Lexicon and Attention based Handwritten Text Recognition System](https://mlsanity.com/paper/2209.04817/) (2022)
- [Quo Vadis Handwritten Text Generation for Handwritten Text Recognition?](https://mlsanity.com/paper/2508.09936/) (2025)
- [A Text Recognition Dataset from Sahidic Coptic Ancient Manuscripts](https://mlsanity.com/paper/2606.15987/) (2026)
- [Motion-Based Handwriting Recognition and Word Reconstruction](https://mlsanity.com/paper/2101.06025/) (2021)
- [Recognizing Handwriting Styles in a Historical Scanned Document Using Unsupervised Fuzzy Clustering](https://mlsanity.com/paper/2210.16780/) (2022)
- [Preserving Privacy Without Compromising Accuracy: Machine Unlearning for Handwritten Text Recognition](https://mlsanity.com/paper/2504.08616/) (2025)
- [A Free Lunch? Adapting PP-OCRv6 for Historical Text Recognition](https://mlsanity.com/paper/2609.20064/) (2026)

## Abstract (arXiv)

Handwritten text recognition is challenging because of the virtually infinite ways a human can write the same message. Our fully convolutional handwriting model takes in a handwriting sample of unknown length and outputs an arbitrary stream of symbols. Our dual stream architecture uses both local and global context and mitigates the need for heavy preprocessing steps such as symbol alignment correction as well as complex post processing steps such as connectionist temporal classification, dictionary matching or language models. Using over 100 unique symbols, our model is agnostic to Latin-based languages, and is shown to be quite competitive with state of the art dictionary based methods on the popular IAM and RIMES datasets. When a dictionary is known, we further allow a probabilistic character error rate to correct errant word blocks. Finally, we introduce an attention based mechanism which can automatically target variants of handwriting, such as slant, stroke width, or noise.