Using Generative Artificial Intelligence to Automate Gravestone Documentation and Analysis

Published in GCH 2026 - Eurographics Workshop on Graphics and Cultural Heritage, 2026

Online cemetery digitization systems are limited by the need for manual information extraction from gravestone photography and content-area expertise in creating informative analyses. These limitations force existing systems to offer search-and-retrieve interfaces with limited context about the burial culture or history of smaller or less prominent cemeteries. Generative artificial intelligence (GenAI) can enhance such systems with automated information extraction, AI-composed analyses and summaries, and interactive conversational interfaces to explore burial culture. We describe the implementation of a multi-lingual information extraction pipeline that combines optical character recognition (OCR) libraries and Vision-Language Models (VLM) and evaluate its effectiveness on a set of gravestones with a variety of scripts, including multi-script gravestones: Latin, Hebrew, and Arabic. A companion article presents additional features implemented, including automatically generated cemetery summaries and a database-grounded conversational interface.

Recommended citation: Michael J. May, Jamal Majadle, Libar Vizman, Netanel Shen, and Efrat Kantor. 2026. Using Generative Artificial Intelligence to Automate Gravestone Documentation and Analysis. In Eurographics Workshop on Graphics and Cultural Heritage (GCH 2026), Ruggero Pintus, Carles Bosch, Carla Schroer, Panagiotis Charalambous, Irina Ciortan, Dimitris Kotzinos, Carlos Andujar, and Domenica Dininno (Eds.). The Eurographics Association. https://doi.org/10.2312/gch.20261080
Download Paper | Download Bibtex