Supported languages

Optical character recognition can recognise a wide range of different languages or different types of text.
Refer to Enum Language in the API REFERENCE for more details on each.

Table 1. OCR Supported languages
Afaan Oromo	Dutch	Interlingua	Moldovan	Slovak
Afrikaans	English (American)	Irish Gaelic	Mongolian (Cyrillic)	Slovenian
Albanian	English (British)	Italian	Nahuatl	Somali
Arabic/*	Esperanto	Japanese*	Nigerian Pidgin	Sotho
Asturian	Estonian	Javanese	No language, Latin alphabet	Spanish
Aymara	Faroese	Kapampangan	Norwegian	Sundanese
Azeri (latin)	Fijian	Kazakh (Cyrillic)	Norwegian Bokmål	Swahili
Balinese	Finnish	Kikongo	Norwegian Nynorsk	Swedish
Banking fonts (cf. API REF)	French	Kinyarwanda	Numeric	Tagalog
Basque	Frisian	Korean*	Nyanja	Tahitian
Belarusian	Friulian	Kurdish	Occitan	Tatar (Latin)
Bemba	Galician	Latin	Papiamento	Tetum
Bikol	Ganda	Latvian	Polish	Thai*
Bislama	German	Lithuanian	Portuguese	Tok pisin
Bosnian (Cyrillic)	German (Switzerland)	Luba	Quechua	Tongan
Bosnian (Latin)	Greek	Luxembourgish	Rhaeto-Romance	Traditional chinese*
Brazilian Portuguese	Greenlandic	Macedonian	Romanian	Tswana
Breton	Haitian Creole	Madurese	Rundi	Turkish
Bulgarian	Hani	Malagasy	Russian	Ukrainian
Catalan	Hebrew*	Malay	Samoan	Uzbek (Latin)
Cebuano	Hiligaynon	Maltese	Sardinian	Vietnamese*
Chamorro	Hungarian	Manx	Scottish Gaelic	Waray
Corsican	Icelandic	Maori	Serbian	Welsh
Croatian	Ido	Mayan	Serbian latin	Wolof
Czech	Ilocano	Mexican Spanish	Shona	Xhosa
Danish	Indonesian	Minangkabau	Simplified chinese*	Zapotec

OCR Extensions required

For Asian languages: Japanese, Korean, Chinese (Simplified/Traditional), Vietnamese and Thai
For Hebrew
For Arabic and Farsi

Table 2. Bank fonts supported by OCR
Type	Specifications	Example
CMC7	MICR (Magnetic ink character recognition code). The character set is limited to the numbers and the five special symbols. The five "special" characters are replaced by ANSI symbols: the internal symbol is by default represented by the symbol "-", the amount symbol as "=", the terminator symbol as "<", the symbol as ";" and the routing symbol as "+". Spaces as they appear in the CMC7 magnetic lines are ignored.
E13b Optical	MICR (Magnetic ink character recognition code). This language limits recognition to the banking font E13B and supports the following character set: the numerals (0 - 9) and four special characters (<, >, + and #).
OCR-A1	OCR-A1 Alphanumeric OCR-A1 Eurobanking OCR-A1 Numeric.
OCR-B1	OCR-B1 Alphanumeric OCR-B1 Eurobanking OCR-B1 Numeric.