Gothic/Fraktur OCR

Language:
EN
Product-Line:
FineReader Engine
Version:
9.x, 10, 11
Type:
Technology & Features
Category:
Recognition, Languages & OCR
  • ABBYY started to develop old font OCR technologies back in 2003 because nothing existed on the market for:
    • Sophisticated “old font” OCR technologies
    • Historical (computer) dictionaries suitable for OCR
    • Language models for analysing and verifying printed historic texts
  • From 2003 on the core recognition technologies were continuously improved.
  • To archive these reduced error rate, optimisations were made in different areas of the technology
    • Image-Preprocessing
    • Document Analysis
    • Character Recognition
    • Language and Dictionary Support


* the numbers are based in internal ABBYY tests on a defined set of documents

ABBYY old Font OCR makes a difference

*Processed with ABBYY Recognition Server 3.0 R1: Gothic/Fraktur enabled/disabled

ABBYY’s role in IMPACT

ABBYY is one of the over 26 European Partners within IMPACT. The Partners have different focus areas:

  • Major European Libraries that “own” the historic materials
  • Scientific Institutions who work in different areas:
    • Linguistics / Computer Linguistic
    • Image Processing
    • Document Analysis
    • Technical implementation and integration of the technologies
  • 2 Industry Partners: ABBYY & IBM Israel

ABBYY

  • Provides the relevant OCR technology for the IMPACT members
  • Develops further improvements of image preprocessing, layout (or page) and analysis of documents
  • Adds OCR-XML output for the recreation of logical document structure
  • Adapts the core OCR components for a full variety of different historical printing materials in European languages

Improvements ABBYY already productised

  • OCR improvements for old European fonts
  • New binarisation is optimized for old doccuments
  • Optimization for old newspapers’ recognition
  • … all these optimisations are already productised and available in FineReader Engine 10 for Windows (and lager
  • OCR adjustment on special samples collected by leading European libraries

Press Release

ABBYY: Recent Developments in Historic OCR

  • ABBYY is the main OCR technology provider for the EU wide IMPACT project to improve access to historical documents
  • The recorded presentation explains improvements delivered from ABBYY for IMPACT

IMPACT Workshop : ABBYY and IMPACT: OCR Introduction and Improvements by Michael Fuchs
from LITIS Laboratory on Vimeo.

Further Information

This website uses cookies which enable you to see pages or use other functions of our websites. You can turn off such cookies in your browser’s settings. If you continue to use these pages, you consent to the use of cookies.