ABBYY Finereader XIX, RNW 422060070001025KN Leaflet

ABBYY FineReader XIX is a special version of the award-winning FineReader optical character recognition (OCR) software

for recognising “fraktur” or “black letter” texts from the period between 1800 and 1938.  It is designed to convert scans of

old documents, books, and papers into text for the purpose of digital archiving and publishing, and it is the first omnifont

OCR software for Fraktur.

Until recently, the limitations of technology and the

unique characteristics of text written in a variety of old-

fashioned fonts and scripts have made it difficult to auto-

mate the process of recording this information via com-

puter.  Sophisticated OCR dictionaries, language models

used for analysing and verifying text written during this

time period, have not existed. Computer systems capable

of reading old texts have required many hours of

systematic training to recognise fonts and characters that

are no longer used in modern printing. 

Black letter fonts, also known as “Gebrochene Schriften”

or broken scripts, first emerged in as early as the 12th

century, and evolved over the years to host a variety of

derivations and font types. The Fraktur typeface,

dominant in Germany, was created on behalf of the

German Emporer Maximilian and soon became popular

in many parts of Europe. Common characteristics and

peculiarities of the type include the elongated s and

ligatures, “joined” letters for certain letter combinations.

The frequency of its application makes understanding of

Fraktur essential for studying text and developing

recognition technologies for the period between 1800

and 1938.

ABBYY FineReader XIX is the first omnifont OCR for

Fraktur, giving users a solution for scanning and convert-

ing old documents with minimal training and dictionary

work.  This was achieved by combining extremely

intelligent technology with dedicated linguistic study:

OCR systems work by analysing a text image and making

a hypothesis about which letter or word an image

represents.  The hypotheses are analysed in context and

verified by use of sophisticated OCR dictionaries made up

of Language Models (LMs).  Language Models (LM) are

computer databases that describe the vocabulary of a

language.  The problem is that modern OCR systems do

not have LMs for older text fonts and older text spellings.

The solution for Fraktur text recognition was achieved

through the development of OCR dictionaries specifically

for this time period.  Special language models were

created for five European languages.

The Fraktur language models were created with the help

of ABBYY partner, ATAPY software.  Through develop-

ment process, 10 different dictionaries and more than

105 books published between 1808 and 1930 were

analysed.  Linguists reviewed word stock, identified

words that have phased out through the evolution of the

languages, and identified the correct paradigm assign-

ments for synchronising the language models with the

appropriate grammar usage for the time period.  More

than 500.000 word entries were manually compared

with existing FineReader dictionaries.  Grammatical

paradigms and word evolutions were reviewed to add

159 historic grammar paradigms that were missing from

the contemporary language models. Language models

were then compiled and tested on a control group of

testing documents featuring old text. 

To recognise the Fraktur style fonts, ABBYY development

teams created special classifiers, or alphabets, capable of

recognising the Fraktur symbols.  As part of this effort,

ABBYY development teams collected a symbol image

base with an average of 2500 symbol samples for each

symbol, a new alphabet pattern, and collected and input

a sample test base representing 31000 pages of text

from different sources.  Using the sample text, the

recognition engine was “fine-tuned” to work with the

subtle features of the Fraktur alphabet (such as the

ligatures, or connected letters). The new alphabet was

then added to the FineReader system and interface and

tested extensively.

ABBYY FineReader XIX was also developed with the

needs of universities and research center in mind.  The

product was developed through a cooperation with the

worldwide METAe Project.  METAe is a consortium of

libraries and digitisation companies from across Europe

who are working together to create the METAe Engine, a

software package specifically designed for organising the

work flow of the archiving and conversion of historical

materials such as books, journals, magazines and news-

papers. ABBYY FineReader XIX will provide a key compo-

nent for archiving some of Europe's most priceless

historical documents.  Partners in the METAe project

include:  the Univeristy of Innsbruck (Austria), University

of Florence (Italy) Bibliotéque Nationale de France, the

National Library of Norway, the Freiedrich-Ebert-

Foundation (Germany), CCS Compact Computer Systeme

(Germany), and Cornell Library University (USA).