What is Gothic/Fraktur font?
Gothic letters (as well known as 'Fraktur' are specific fonts that were used in documents in the begining of the 19th century - these letters cannot be recognized with standard OCR technologies. ABBYY is a pioneer in this area and provides recognition of old fonts in several of its products and technologies.
The below animation demonstrates the difference in recognition results: Using a 'Standard OCR' vs. using a specific technology for recognition of historic fonts*.
*The original image was processed with ABBYY Recognition Server 3.0 R1 with the Gothic/Fraktur module disabled (standard OCR used) and the Gothic/Fraktur module enabled (Historic font OCR)
ABBYY started providing the Gothic recognition already back in 2003 and its core recognition technologies are being continuously improved by optimizing the individual areas of the recognition process:
Language and Dictionary Support
ABBYY’s role in the IMPACT project
ABBYY was the main OCR technology provider for the IMPACT project funded by the European Commission to significantly improve access to historical text and to take away the barriers that stand in the way of the mass digitisation of the European cultural heritage.
ABBYY provided the relevant OCR technology for the IMPACT members, developed further improvements of image preprocessing, layout (or page) and analysis of documents, added OCR-XML output for the recreation of logical document structure and adapted the core OCR components for a full variety of different historical printing materials in European languages. The improvements in ABBYY technologies were implemented in many ABBYY products, such as the SDK ABBYY FineReader Engine, the corporate-wide automation solution ABBYY FineReader Server, and the individual application ABBYY FineReader PDF.
Impact Press Release: ABBYY Empowers European Commission's Digitisation Research Project