Metraipolis › archive › dc_da44ac3e30be
Rethinking Handwritten Character Recognition — arXiv:2609.10572
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.10572
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T06:28:45.857Z
- SHA-256 of the archived text
6e41a050fc932493fc40efd39339d3d7f35aa31674e7c5166ed80a9f809792e1- Stable URL of this page
https://metraipolis.com/documento/dc_da44ac3e30be
How to cite
Rethinking Handwritten Character Recognition — arXiv:2609.10572 — arXiv (en), https://arxiv.org/abs/2609.10572 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_da44ac3e30be (Metraipolis archive dc_da44ac3e30be, sha256 6e41a050fc932493fc40efd39339d3d7f35aa31674e7c5166ed80a9f809792e1)
BibTeX
@misc{dcda44ac3e30be,
title = {Rethinking Handwritten Character Recognition — arXiv:2609.10572},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.10572},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_da44ac3e30be; sha256 6e41a050fc932493fc40efd39339d3d7f35aa31674e7c5166ed80a9f809792e1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.10572. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-11 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Image and Video Processing (eess.IV). Pagina del lavoro: https://arxiv.org/abs/2609.10572 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T06:06:28.734Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).