Applying End-to-end Trainable Approach on Stroke Extraction in Handwritten Math Expressions Images - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Applying End-to-end Trainable Approach on Stroke Extraction in Handwritten Math Expressions Images

Résumé

In this paper, we propose a novel end-to-end system to extract strokes from offline math expressions. Using a multi-task neural network we simultaneously predict the location of the pen and the pen state. Our approach is based on a recent state-of-the-art image-to-sequence method limited to small fixed-sizes images. We generalize it to large and multi-symbol images without preprocessing steps such as skeletonization or binarization. This architecture allows an end-to-end training. A curriculum learning strategy have been used to address the complexity of the images. We achieve comparable results to the state of the art on the UNIPEN English character dataset considering the next point prediction. We propose a stroke level metrics that allows us to measure the stroke reconstruction. Experiments show the advantages and limitations of the adopted Image-to-Sequence method when scaling up to large and complex images such as math equations.
Fichier principal
Vignette du fichier
ICDAR2021_paper289_VF.pdf (476.55 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03236506 , version 1 (29-09-2021)

Identifiants

Citer

Elmokhtar Mohamed Moussa, Thibault Lelore, Harold Mouchère. Applying End-to-end Trainable Approach on Stroke Extraction in Handwritten Math Expressions Images. ICDAR 2021 : 16th International Conference on Document Analysis and Recognition, Sep 2021, Lausanne, Switzerland. ⟨10.1007/978-3-030-86334-0_29⟩. ⟨hal-03236506⟩
176 Consultations
193 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More