Case Study: National Library of Latvia creates a searchable digital archive of 4 million pages with ABBYY FineReader Engine

ABBYY FineReader® Preserves the National Library of Latvia for Future Generations

The National Library of Latvia faced the challenge of preserving and opening access to a 4.5 million–unit collection—including rare books, periodicals and materials in Latvian, Russian and archaic European fonts—that was deteriorating and largely available only as image-only scans that weren’t searchable. The library needed high‑quality OCR that could handle Latvian and historic Fraktur/Antiqua typefaces to create a usable digital archive.

Using CCS’s docWorks built on ABBYY FineReader Engine, the library ran a large-scale OCR project that processed roughly 4 million pages in about a year (with teams of operators working in shifts). Documents were exported to PDF, JPEG and XML and published via the periodicals portal (periodika.lv), making historically important and public-domain materials searchable and accessible to researchers and the public.

National Library of Latvia

Joachim Bauer

Head of docWorks Group