Case Study: China National Knowledge Infrastructure (CNKI) achieves fast, accurate mass digitization and searchable digital knowledge with ABBYY FineReader Engine (ABBYY)

ABBYY FineReader® Engine Transforms Scientific Papers into Digital Knowledge

China National Knowledge Infrastructure (CNKI is China’s national digital library covering journals, dissertations, newspapers, patents and more) faced a massive digitization challenge: millions of pages in many languages, rich with illustrations, tables and diagrams, had to be converted into searchable, standards-compliant CAJ files and indexed for fast retrieval. Manual conversion was too slow and earlier OCR attempts only supported Chinese, produced low-quality results and failed to preserve document layouts.

CNKI engaged Shanghai Taibi to integrate ABBYY FineReader Engine, using multi-core, two-stage processing (full-text OCR plus metadata capture) to preserve layouts and export to Word, Excel, searchable PDF/A and CAJ. The solution delivered higher accuracy with a single verifier, cut processing time from weeks to days, freed staff from manual retyping, and made China’s academic knowledge far more accessible and searchable.

CNKI

Wu

Technical Director