Readiris recognizes all American and European languages, including the Baltic, Central-European languages, Greek and the Cyrillic (Russian) languages.
Optionally, you can read the Asian languages Japanese, Simplified Chinese, Traditional Chinese and Korean.
The list of recognized characters varies according to the selected document language.
Readiris can switch languages in the middle of a sentence without any help from the user!
When Western words pop up in Greek, Cyrillic or Asian documents - many untranscribable proper names, brand names etc. are written using the familiar Western symbols -, Readiris can switch to the correct alphabet automatically. You can activate a mixed alphabet of Greek, Cyrillic (Russian) or Asian and Western characters!
Recognition is assisted by linguistic databases. Readiris extensively uses linguistic information to validate good solutions and mark suspicious ones.
Limit recognition to a numeric character set to optimally OCR tables of figures. The symbols 0 to 9, +, *, /, %, ,, ., (, ), -, =, $, £, ₯ and the symbol will be recognized. Do not select this option when your tables contain text!
When you select Cyrillic-English, Greek-English or an Asian language, a mixed character set is used. Readiris copes beautifully with Western words (proper names etc.) as occur in Russian, Greek and Asian documents.
Tip: select the document language before executing the page analysis when you are dealing with Asian documents. Specific page analysis routines are used for Asian documents.
To mix languages on a page, select the language with the most extended character set.
To read documents where the French translation occurs alongside an English text, select French as language to ensure that the accentuated characters - such as η, ι and ω - get recognized correctly.
The French lexicon will provide linguistic feedback to the OCR process; no linguistics are used to validate the English text!
Tip: the tooltip of the Language button enumerates the selected language.