Accessible Graphics: Semantic graphic description in PDFs for visually impaired people

• Unité de recherche: INNOSUISSE
• Numéro de projet: 108.047 IP-ICT
• Titre du projet anglais: Accessible Graphics: Semantic graphic description in PDFs for visually impaired people

Mots-clé (Anglais)

ICT, Deep learning

Résumé des résultats (Abstract) (Anglais)

The goal of this project is to research and develop deep-learning based methods to automatically extract the data visualized in a chart, in order to generate a semantic description of the chart graphics for visually impaired readers using their screen readers.