Automated Extraction of Icon-based Tables
This paper introduces a novel algorithm specifically designed to address the unique complexities of icon-based tables in digital documents. Our algorithm leverages a combination of computer vision techniques to accurately detect table grids, identify symbols, and insert them into their relative positions.
Thome, B., F. Hertweck PhD, L. Jonas, S. Yasar and S. Conrad (2024), Automated Extraction of Icon-based Tables. In Maike Klein, Daniel Krupka, Cornelia Winter, Martin Gergeleit and Ludger Martin (Hrsg.), INFORMATIK 2024 Proceedings: Lock-in or log out? Wie digitale Souveränität gelingt. Bonn: Gesellschaft für Informatik (GI), 2001 - 2003.
DOI: 10.18420/inf2024_173