Languages can be recognized if the OCR engine supports that language's character set. LEADTOOLS recognizes dozens of languages, enumerated in DOC2_LANGIDS.
In addition, many recognized languages also have spelling dictionaries, enabling spell-checking after character recognition is complete. Languages for which spell-checking is supported are listed below, along with their associated dictionary file.
OCR Professional
All languages to be recognized can be selected using L_Doc2SelectLanguages.
The language dictionary to use for spell-checking should be specified in the SpellLangId member of the pRecogOpts parameter passed to the L_Doc2Recognize function.
For more information on options for the recognition process, refer to RECOGNIZEOPTS2.
SPELL-CHECK LANGUAGE |
LANGUAGE DICTIONARY FILE |
Catalan |
R_CAT.DAT |
Czech |
R_CZH.DAT |
Danish |
R_DAN.DAT |
Dutch |
R_DUT.DAT |
English |
R_ENG.DAT |
Finnish |
R_FIN.DAT |
French |
R_FRE.DAT |
German |
R_GER.DAT |
Greek |
R_GRE.DAT |
Hungarian |
R_HUN.DAT |
Italian |
R_ITA.DAT |
Norwegian |
R_NOR.DAT |
Polish |
R_POL.DAT |
Portuguese |
R_POR.DAT |
Russian |
R_RUS.DAT |
Slovenian |
R_SLN.DMD |
Spanish |
R_SPA.DAT |
Swedish |
R_SWE.DAT |
Note: Also requires the file ICHUNW32.DLL.
For more information, refer to: