# Rethinking Handwritten Character Recognition

arXiv: https://arxiv.org/abs/2609.10572 · HTML: https://mlsanity.com/paper/2609.10572/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 55 references that are in the map.
- First posted on arXiv 2 Sep 2026.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Group Equivariant Convolutional Networks](https://mlsanity.com/paper/1602.07576/) (2016)
- [Dynamic Routing Between Capsules](https://mlsanity.com/paper/1710.09829/) (2017)
- [Deep Learning for Classical Japanese Literature](https://mlsanity.com/paper/1812.01718/) (2018)
- [Inductive Biases for Deep Learning of Higher-Level Cognition](https://mlsanity.com/paper/2011.15091/) (2020)
- [SpinalNet: Deep Neural Network with Gradual Input](https://mlsanity.com/paper/2007.03347/) (2020)
- [An Ensemble of Simple Convolutional Neural Network Models for MNIST Digit Recognition](https://mlsanity.com/paper/2008.10400/) (2020)
- [WaveMix: A Resource-efficient Neural Network for Image Analysis](https://mlsanity.com/paper/2205.14375/) (2022)
- [Kannada-MNIST: A new handwritten digits dataset for the Kannada language](https://mlsanity.com/paper/1908.01242/) (2019)
- [Boosting Modern and Historical Handwritten Text Recognition with Deformable Convolutions](https://mlsanity.com/paper/2208.08109/) (2022)
- [Spectral Response Function Guided Deep Optimization-driven Network for Spectral Super-resolution](https://mlsanity.com/paper/2011.09701/) (2020)
- [ResDepth: A Deep Residual Prior For 3D Reconstruction From High-resolution Satellite Images](https://mlsanity.com/paper/2106.08107/) (2021)
- [TextCaps : Handwritten Character Recognition with Very Small Datasets](https://mlsanity.com/paper/1904.08095/) (2019)
- [VIPriors 2: Visual Inductive Priors for Data-Efficient Deep Learning Challenges](https://mlsanity.com/paper/2201.08625/) (2022)
- [HCR-Net: A deep learning based script independent handwritten character recognition network](https://mlsanity.com/paper/2108.06663/) (2021)
- [IB-U-Nets: Improving medical image segmentation tasks with 3D Inductive Biased kernels](https://mlsanity.com/paper/2210.15949/) (2022)
- [Stroke Extraction of Chinese Character Based on Deep Structure Deformable Image Registration](https://mlsanity.com/paper/2307.04341/) (2023)
- [The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases](https://mlsanity.com/paper/2411.09827/) (2024)
- [Capsule Deep Neural Network for Recognition of Historical Graffiti Handwriting](https://mlsanity.com/paper/1809.06693/) (2018)
- [Spatially Dependent U-Nets: Highly Accurate Architectures for Medical Imaging Segmentation](https://mlsanity.com/paper/2103.11713/) (2021)
- [Recognition of Handwritten Japanese Characters Using Ensemble of Convolutional Neural Networks](https://mlsanity.com/paper/2306.03954/) (2023)

## Abstract (arXiv)

Non-Latin handwritten character recognition (HCR) remains understudied. Dominant methods consider it as generic image classification, which uses model scale to implicitly learn stroke structure. Structural-prior efficiency---the principle that explicitly encoding script-geometric regularities as architectural inductive biases can be both more accurate and require fewer parameters. We introduce GraphemeNet, a unified multi-script architecture, governed by two orthogonal binary axes. Axis 1 operationalises stroke-level geometric regularity via Persistent Scaffold Injection (PSI): a script-specific asymmetric convolution injects a stroke scaffold as a weighted residual at every encoder stage, continuously anchoring learned features to script geometry---distinct from skip connections, auxiliary losses, or attention reweighting. Axis 2 selects between global average pooling with gated fusion and cross-scale attention with a Stroke Topology Module (STM), depending on whether glyph discrimination requires spatial relational reasoning. A Linear Capsule Routing (LCR) with O(n) routing is shared universally. On fourteen benchmarks across eight writing systems, the architecture generalises with only scaffold and decoder topology varying per script, consistently challenging, outperforming published baselines, and establishing structural-prior efficiency as a broadly applicable principle for multi-script HCR.