Case Study: Genealogy Indexer achieves searchable access to over 1 million historical pages with ABBYY Recognition Server

Award-Winning Genealogy Website Makes 1 Million Document Pages Searchable With ABBYY OCR

Genealogy Indexer is a nonprofit, free website that makes historical records—primarily Jewish community directories and other sources from Central and Eastern Europe—full-text searchable. The project faced the challenge of converting more than one million pages spanning three centuries and 20 languages into searchable digital files: many source documents were large, low-quality scans, printed in hard-to-recognize typefaces (including Fraktur), and manual transcription was impractical at scale.

To meet that need the founder standardized on ABBYY OCR technology—first FineReader and then server-based Recognition Server—to perform automated, high-volume OCR (including Fraktur) and integrate output and metadata into the site’s search engine via custom automation. The result: roughly one million pages are now searchable (including ~900,000 pages of directories, 114,000 pages of yizkor books, 32,000 pages of military lists, 43,000 pages of community histories, and 24,000 pages of school records), users run 4,000–5,000 searches daily, and the site can reliably surface documents that were previously inaccessible.

Genealogy Indexer

Logan Kleinwaks

Founder