Supported CPU and Operating Systems

The OCR SDK for Embedded OS is currently compatible with many CPU types and operating systems and can be ported to virtually any CPU type and any OS on demand.

CPU types supported

  • x86 (Intel Atom, Core 2)
  • ARM
  • PowerPC
  • and any other (on demand)

Operating systems supported

  • Windows for x86 processors (Windows CE, Windows XP Embedded)
  • Linux, ucLinux
  • VXWorks
  • NetBSD
  • FreeBSD
  • Android
  • and any other (on demand)

Development Platform

C/C++

Storage Memory Requirements (ROM)

  • 1160 MB for the library (depending on the functionality included)
  • 0.51 MB for the language module of each supported recognition language, 16 MB for CJK pattern
  • 0.55 MB for the dictionary of each supported recognition language (optional).

The library can be stored either in ROM or RAM depending on the specific device.

Runtime Memory Requirements (RAM)

  • 1160 MB for the library (depending on the functionality included)
  • 0.51 MB for the language module of each supported recognition language, 16 MB for CJK pattern
  • 0.5–5 MB for the dictionary of each supported recognition language (optional)
  • 1017 MB or more for program operation (depending on the image size, colority and quality: 1012 MB for small photo pictures, about 1017 MB for an A4 business letter).

Supported OCR Languages

23 languages with dictionary support:

Bulgarian, Czech, Dutch, Dutch Belgian, English, Estonian, Finnish, French, German, German New Spelling, Greek, Indonesian, Italian, Norwegian Bokmal, Norwegian Nynorsk, Polish, Portuguese, Portuguese Brazilian, Russian, Spanish, Swedish, Turkish, and Ukrainian.

37 languages without dictionary support:

Afrikaans, Albanian, Basque, Breton, Belarusian, Catalan, Chechen, Crimean Tatar, Croatian, Fijian, Hawaiian, Hungarian, Icelandic, Indonesian, Irish, Kabardian, Latin, Latvian, Lithuanian, Macedonian, Malay, Maori, Moldavian, Mongol, Ossetic, Provencal, Rhaeto Romanic, Romanian, Samoan, Serbian, Slovak, Slovenian, Swahili, Tagalog, Tatar, Welsh,  and Yiddish.

CJK languages:

Chinese Simplified, Chinese Traditional, Japanese, Korean

More than 130 other languages can be added upon request – contact the ABBYY team.

Supported Import and Export Formats

Import formats: BMP, TIFF, multi-image TIFF, GIF, PCX, DCX, JPEG, JPEG 2000
Additional import format for customized solutions: PDF image only

Export formats: TXT, PDF, PDF/A, PDF with MRC, ABBYY XML for Embedded, vCard
Additional export formats for customized solutions: RTF, DOC/DOCX, XLS/XLSX, PPT/PPTX, HTML, CSV

Support for any other formats can be provided upon request. For details, please contact the ABBYY team.

Image Pre-processing

Available image pre-processing options include:

  • Adaptive Binarization
  • Deskewing
  • Automatic page orientation

Business Card Recognition Specifications

Business Card Reader recognizes business cards in 23 languages:

Chinese Simplified, Chinese Traditional, Danish, Dutch, English, Estonian, Finnish, French, German, Greek, Indonesian, Italian, Japanese, Korean, Norwegian, Polish, Portuguese, Portuguese (Brazilian), Russian, Spanish, Swedish, Turkish, and Ukrainian.

Business Card Reader can be taught additional languages on demand - contact the ABBYY team.

Want to try?

Contact sales team for more information or request a free trial

Usage of Cookies. In order to optimize the website functionality and improve your online experience ABBYY uses cookies. You agree to the usage of cookies when you continue using this site. Further details can be found in our Cookie Policy.