Hybrid Metadata Extraction from League of Nations Index Cards: From Feasibility Study to Archival System Integration
This work provides a practical solution for extracting metadata from historical index cards, benefiting archival institutions seeking to digitize and integrate legacy finding aids.
The project developed a hybrid AI workflow to extract metadata from League of Nations index cards, achieving integration into the LONTAD archival system. The final architecture uses a fine-tuned vision-language model for broad extraction and specialized OCR for identifiers, improving access to archival descriptions and digital objects.
This project report presents a hybrid AI-assisted workflow for extracting and reintegrating archival metadata from League of Nations index cards. The project is situated in the broader context of the Total Digital Access to the League of Nations Archives project (LONTAD). Rather than attempting full OCR of the underlying archival collections, the workflow targets the index cards themselves as documentary access points to files, series, archival descriptions, and digital objects. The project evolved from a layout-aware pipeline combining YOLO, TrOCR, and local LLM post-correction to a hybrid architecture using a fine-tuned vision-language model for broad extraction while retaining specialized OCR for file and series identifiers.