Case Study: Fraunhofer IMK opens 225 years of NZZ archive for full-text search with ABBYY FineReader XIX (ABBYY)

Fraunhofer - Customer Case Study

The Fraunhofer Institute for Media Communication (IMK) partnered to digitise the Neue Zürcher Zeitung’s 225‑year archive—about two million pages stored on roughly 1,500 rolls of 35‑mm microfilm. The project faced large scale, highly variable microfilm quality with distortions and the mixed use of roman and gothic typefaces; as Dr. Stefan Eickeler, IMK Project Manager, explains, these factors required special solutions for reliable text recognition.

IMK combined its own image‑preprocessing software with ABBYY FineReader XIX and the FineReader Engine SDK, running the workflow on a 20‑node cluster to produce per‑page XML files (~4 MB each). The automated OCR of gothic and roman print opened the archive to full‑text search and made the digitisation feasible and cost‑effective, producing a complete digital inventory of about 10 TB—an outcome ABBYY Europe CEO Jupp Stoepetie credits to advances in OCR technology.

Fraunhofer

Stefan Eickeler

IMK Project Manager