The paper investigates self‑supervised pretraining for Handwritten Text Recognition (HTR) and finds that pixel‑reconstruction methods outperform contrastive methods, a contrast to natural‑image classification. The authors argue that discriminative information for HTR is concentrated in high‑variance pixel directions, and they test six SSL methods across six handwriting benchmarks in five languages, showing that pixel‑grounded approaches achieve the lowest character error rates and are more label‑efficient. When combined with a pretrained LLM decoder, a frozen pixel‑grounded encoder rivals fully fine‑tuned supervised baselines, underscoring the importance of aligning representations with high‑variance pixel subspaces.
arXiv:2609.37195v1 Announce Type: new Abstract: Handwritten Text Recognition (HTR) systems have become an indispensable tool for the digitization of historical documents. Not only do they cut down ti...
arXiv:2609.01147v1 Announce Type: cross Abstract: Text-rich visual inputs require models that can read, retrieve, and compress language directly in pixel space, yet existing pixel-text encoders strug...
To train handwritten text recognition systems we need word images and their corresponding transcriptions, and these transcriptions are produced manually. For a script that can be read by only a small...
arXiv:2609.16859v1 Announce Type: cross Abstract: To train handwritten text recognition systems we need word images and their corresponding transcriptions, and these transcriptions are produced manua...
inkGround is a new benchmark for evaluating how well Vision‑Language Models can recover the fine‑grained stroke trajectories of cursive handwriting from camera‑captured page images. It contains 537 full‑page images with 18.7k words and 163k strokes, paired with pseudo‑trajectory references generated by an offline‑to‑online model and verified by humans. The benchmark casts the task as text‑conditioned point grounding, scoring models on trajectory fidelity, readability, and style similarity, and compares both open‑source and closed‑source VLMs, showing that closed‑source models like Gemini‑3.1‑Pro perform best.
OmniHandwritingOCR is a diagnostic benchmark designed to evaluate multimodal large language models (MLLMs) and OCR systems on handwritten text and mathematical expression recognition. It comprises 77.57K labeled images across six subtasks and twelve subsets, including a difficulty‑stratified multi‑line formula corpus that tests robustness to increasing structural complexity. The benchmark reveals that current systems perform poorly on complex multi‑line formulas, exhibit variable rankings across languages and formula settings, and sometimes hallucinate corrections that are not visually supported.
The paper introduces GraphemeNet, a unified multi‑script handwritten character recognition architecture that explicitly encodes script‑geometric regularities. It uses two orthogonal binary axes: Persistent Scaffold Injection (PSI) to embed stroke‑level geometry into each encoder stage, and a choice between gated global pooling or a Stroke Topology Module for spatial relational reasoning. Across fourteen benchmarks in eight writing systems, GraphemeNet achieves state‑of‑the‑art performance with fewer parameters, demonstrating the effectiveness of structural‑prior efficiency for multi‑script HCR.
The paper introduces a Hybrid Deep Learning (HDL) architecture that combines Auto-Learned Features (ALF) and Human-Engineered Features (HEF) for handwriting verification. ALF is extracted using a Two Channel Convolutional Neural Network (TC-CNN) or a Two Channel Autoencoder (TC-AE), while HEF is obtained via Gradient Structural Concavity (GSC) or Scale Invariant Feature Transform (SIFT). Experiments on 150,000 pairs of the word "AND" from 1,500 writers show that the HDL model using AE-GSC achieves 99.7% accuracy on a seen writer dataset and 92.16% on a shuffled writer dataset, outperforming CEDAR-FOX, and AE-SIFT performs comparably on unseen writers.
arXiv:2603. 16883v2 Announce Type: replace-cross Abstract: Inertial measurement unit-based online handwriting recognition enables the recognition of input signals collected across different writing surfaces but remains challenged by uneven character distributions and inter-writer variability.
Pixel language models treat text as rendered images, enabling strong cross‑lingual transfer. This study trains MPIXEL models varying languages, scripts, and capacity while keeping per‑language compute constant, and evaluates them on five tasks across 83 languages. Results show that scaling improves performance on added languages and scripts, mitigates the curse of multilinguality, and outperforms subword and character baselines on typologically distant low‑resource languages, though transfer to unseen scripts does not benefit further from scaling.
ExpertHTR is a unified vision‑language framework for handwritten text recognition that tackles the challenge of small, heterogeneous datasets by organizing structural annotations into a common Page‑Region‑Line representation. It defines four related training tasks—complete transcription, physical‑line coverage, text localization, and localized recognition—without extra manual labels. The model combines a jointly trained dense backbone with a sparse Mixture‑of‑Experts architecture, using Sparsegen routing and regularization to adaptively activate experts, achieving state‑of‑the‑art results on the IAM benchmark and outperforming general‑purpose OCR systems on most datasets.
arXiv:2608.30541v1 Announce Type: new Abstract: Pixel-based language models (LMs) replace traditional tokenizers by processing rendered images of text, making cross-lingual transfer heavily dependent...