Recognition languages

Below you can find the list of recognition languages supported by ABBYY Cloud OCR SDK (can be used for OCR).

The internal profile name is the language name. Exceptions are specified in italics.

× — can be used for ICR

× — can be used for BCR

Abkhaz

Adyghe

Afrikaans×

Agul

Albanian×

Altaic

Arabic (Saudi Arabia) | Arabic

Armenian (Eastern) | ArmenianEastern

Armenian (Grabar) | ArmenianGrabar

Armenian (Western) | ArmenianWestern

Avar

Aymara×

Azerbaijani (Cyrillic) | AzeriCyrillic

Azerbaijani (Latin) | AzeriLatin ×

Bashkir

Basque×

Belarussian | Belarusian

Bemba×

Blackfoot×

Breton×

Bugotu×

Bulgarian×

Buryat×

Catalan

Chamorro×

Chechen

Chinese Simplified | ChinesePRC ×

Chinese Traditional | ChineseTaiwan ×

Chukcha

Chuvash

For MICR CMC-7 text type | CMC7

Corsican×

Crimean Tatar | CrimeanTatar

Croatian×

Crow×

Czech××

Danish××

Dargwa

Numbers* | Digits×

Dungan

Dutch (Netherlands) | Dutch××

Dutch (Belgium) | DutchBelgian

For MICR (E-13B) text type | E13B

English××

Eskimo (Cyrillic) | EskimoCyrillic

Eskimo (Latin) | EskimoLatin

Esperanto

Estonian××

Even×

Evenki×

Farsi

Faeroese

Fijian×

Finnish××

French××

Frisian×

Friulian×

Scottish Gaelic | GaelicScottish×

Gagauz

Galician×

Ganda×

German××

German (Luxembourg) | GermanLuxembourg×

German (new spelling) | GermanNewSpelling×

Greek××

Guarani×

Hani×

Hausa

Hawaiian×

Hebrew

Hungarian××

Icelandic

Ido×

Indonesian××

Ingush

Interlingua×

Irish×

Italian××

Japanese×

Kabardian

Kalmyk

Karachay-Balkar | KarachayBalkar×

Karakalpak

Kasub×

Kawa×

Kazakh×

Khakas

Khanty

Kikuyu

Kirgiz×

Kongo×

Korean×

Korean (Hangul) | KoreanHangul

Koryak

Kpelle×

Kumyk×

Kurdish×

Lak

Sami (Lappish) | Lappish×

Latin×

Latvian×

Latvian language written in Gothic script | LatvianGothic

Lezgin

Lithuanian×

Luba×

Macedonian

Malagasy×

Malay

Malinke×

Maltese

Mansi

Maori×

Mari

Maya×

Miao×

Minangkabau×

Mohawk×

Mongol×

Mordvin×

Nahuatl×

Nenets×

Nivkh×

Nogay×

NorwegianNynorsk + NorwegianBokmal | Norwegian×

Norwegian (Bokmal) | NorwegianBokmal××

Norwegian (Nynorsk) | NorwegianNynorsk××

Nyanja×

Occidental

Ojibway×

Old English | OldEnglish×

Old French | OldFrench×

Old German | OldGerman×

Old Italian | OldItalian×

Old Slavonic | OldSlavonic

Old Spanish | OldSpanish×

Ossetian

Papiamento×

Tok Pisin | PidginEnglish×

Polish××

Portuguese (Brazil) | PortugueseBrazilian××

Portuguese (Portugal) | PortugueseStandard××

Provencal

Quechua×

Rhaeto-Romanic | RhaetoRomanic×

Romanian×

Romanian (Moldavia) | RomanianMoldavia×

Romany×

Ruanda×

Rundi×

Russian (old spelling) | RussianOldSpelling

Russian××

Samoan×

Selkup×

Serbian (Cyrillic) | SerbianCyrillic×

Serbian (Latin) | SerbianLatin×

Shona

Sioux (Dakota)×

Slovak×

Slovenian×

Somali×

Sorbian

Sotho×

Spanish××

Sunda

Swahili×

Swazi×

Swedish××

Tabassaran

Tagalog×

Tahitian×

Tajik×

Tatar

Thai

Jingpo×

Tongan×

Tswana×

Tun×

Turkish××

Turkmen

Tuvan×

Udmurt

Uighur (Cyrillic) | UighurCyrillic

Uighur (Latin) | UighurLatin×

Ukrainian××

Uzbek (Cyrillic) | UzbekCyrillic

Uzbek (Latin) | UzbekLatin×

Vietnamese

Cebuano | Visayan×

Welsh

Wolof

Xhosa×

Yakut

Yiddish

Zapotec×

Zulu

* Besides the ten digits 0123456789, the Digits predefined language contains the following characters:

punctuation marks ()+,-./:=
#$([{¢£€ characters are allowed to precede the word
%).]}°¼½¾ characters are allowed after the word

So you can recognize sequences like "$450" or "12%" using this predefined language.

Nikolai Kromm

Comments

Recently viewed