The Return of Structural Handwritten Mathematical Expression Recognition

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Seitz, Jakob, Lengfeld, Tobias, Timofte, Radu
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916921055641600
author Seitz, Jakob
Lengfeld, Tobias
Timofte, Radu
author_facet Seitz, Jakob
Lengfeld, Tobias
Timofte, Radu
contents Handwritten Mathematical Expression Recognition is foundational for educational technologies, enabling applications like digital note-taking and automated grading. While modern encoder-decoder architectures with large language models excel at LaTeX generation, they lack explicit symbol-to-trace alignment, a critical limitation for error analysis, interpretability, and spatially aware interactive applications requiring selective content updates. This paper introduces a structural recognition approach with two innovations: 1 an automatic annotation system that uses a neural network to map LaTeX equations to raw traces, automatically generating annotations for symbol segmentation, classification, and spatial relations, and 2 a modular structural recognition system that independently optimizes segmentation, classification, and relation prediction. By leveraging a dataset enriched with structural annotations from our auto-labeling system, the proposed recognition system combines graph-based trace sorting, a hybrid convolutional-recurrent network, and transformer-based correction to achieve competitive performance on the CROHME-2023 benchmark. Crucially, our structural recognition system generates a complete graph structure that directly links handwritten traces to predicted symbols, enabling transparent error analysis and interpretable outputs.
format Preprint
id arxiv_https___arxiv_org_abs_2508_19773
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Return of Structural Handwritten Mathematical Expression Recognition
Seitz, Jakob
Lengfeld, Tobias
Timofte, Radu
Computer Vision and Pattern Recognition
Handwritten Mathematical Expression Recognition is foundational for educational technologies, enabling applications like digital note-taking and automated grading. While modern encoder-decoder architectures with large language models excel at LaTeX generation, they lack explicit symbol-to-trace alignment, a critical limitation for error analysis, interpretability, and spatially aware interactive applications requiring selective content updates. This paper introduces a structural recognition approach with two innovations: 1 an automatic annotation system that uses a neural network to map LaTeX equations to raw traces, automatically generating annotations for symbol segmentation, classification, and spatial relations, and 2 a modular structural recognition system that independently optimizes segmentation, classification, and relation prediction. By leveraging a dataset enriched with structural annotations from our auto-labeling system, the proposed recognition system combines graph-based trace sorting, a hybrid convolutional-recurrent network, and transformer-based correction to achieve competitive performance on the CROHME-2023 benchmark. Crucially, our structural recognition system generates a complete graph structure that directly links handwritten traces to predicted symbols, enabling transparent error analysis and interpretable outputs.
title The Return of Structural Handwritten Mathematical Expression Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.19773