ABBYY FineReader EngineThe most comprehensive OCR SDK for software developers
Integrate AI-powered OCR features into your applications.
Specifications
ABBYY FineReader Engine 12 is available in three versions:
- ABBYY FineReader Engine 12 for Windows
- ABBYY FineReader Engine 12 for Linux
- ABBYY FineReader Engine 12 for Mac
System requirements
Hardware
PC with x86-compatible processor (1 GHz or higher)
Operating system
Tested Cloud and virtual environments
- Azure App Services
- Azure Cloud Services
- Azure Service Fabric
- Azure Virtual Machines
- Amazon EC2
- Microsoft Hyper-V Server 2008
- Microsoft Hyper-V Server 2008 R2 SP1
- Microsoft Hyper-V Server 2012
- Microsoft Hyper-V Server 2012 R2
- Microsoft Hyper-V Server 2016
- Oracle VM VirtualBox 5.2
- Parallels Desktop for Mac 13.0.1
- VMware ESXi 6.5
- VMware Workstation Player 12.5
- VMware Workstation Pro 14.0.0
ABBYY FineReader Engine can also be run in a Docker container on supported platforms.
Tested Java development environments
ABBYY FineReader Engine Java wrapper has been tested on the following Java Development Kits:
- for 32-bit operating systems:
- Oracle Java SE Development Kit 8u201 i586
- Oracle Java SE Development Kit 8u202 i586
- for 64-bit operating systems:
- OpenJDK 11.0.2 x64
- OpenJDK 12.0.2 x64
- OpenJDK 13 x64
- Oracle Java SE Development Kit 8u201 x64
- Oracle Java SE Development Kit 8u202 x64
- Oracle Java SE Development Kit 11.0.2 x64
- Oracle Java SE Development Kit 12.0.2 x64
- Oracle Java SE Development Kit 13 x64
Memory
- for processing one-page documents — minimum 400 MB RAM, recommended 1 GB RAM
- for processing multi-page documents — minimum 1 GB RAM, recommended 1,5 GB RAM
- for parallel processing — 450 MB RAM + 350 MB RAM for each core
- for parallel processing of documents in Arabic, Chinese, Japanese or Korean languages — 750 MB RAM + 850 MB RAM for each core
Hard disk space
- 1.600 MB for library installation (core functionality)
- Additional 400 MB for installation of the OfficeConverters module library
- 100 MB for program operation
- Additional 15 MB for every page when processing a multi-page document
Other requirements
- TWAIN-compatible scanner, digital camera, or fax modem for scanning or image import
- For pattern training, dictionary editing, scanning via a GUI: Video card and monitor (minimum resolution 1024×768)
- Microsoft® Internet Explorer 8.0 or higher should be installed. For correct font detection, the fonts contained in documents should be installed.
ABBYY SDK 12 licensing service requirements
Hardware
PC with x86-compatible processor (1 GHz or higher)
Operating system
- Windows Server 2016, Windows Server 2012 R2, Windows Server 2012, Windows Server 2008 R2
- Windows 10, Windows 8.1, Windows 8, Windows 7 SP1
ABBYY SDK 12 Licensing Service has been tested in the following virtual environments:
- Microsoft Hyper-V Server 2008
- Microsoft Hyper-V Server 2008 R2 SP1
- Microsoft Hyper-V Server 2012
- Microsoft Hyper-V Server 2012 R2
- Microsoft Hyper-V Server 2016
- Oracle VM VirtualBox 5.2
- Parallels Desktop for Mac 13.0.1
- VMware ESXi 6.5
- VMware Workstation Player 12.5
- VMware Workstation Pro 14.0.0
Developing Tools
The ABBYY FineReader Engine for Windows’ application programming interface (API) conforms to the COM standard and can be easily used in C/C++, Visual Basic, .NET, Delphi, Java or any development tool supporting COM components. The Engine can be adapted for use in scripting languages like VBS, JS, and Perl.
ABBYY FineReader Engine 12 for Linux is designed for glibc version 2.11 and above. If you need ABBYY FineReader Engine for older glibc versions, please contact the ABBYY office. For the FineReader Engine dynamic library, the standard libstdc++.so.6, libgcc_s.so.1 and libgomp.so.1 libraries have to be used.
Hardware
PC with x86-compatible processor (1 GHz or higher) which supports SSE and SSE2 instruction sets
Operating system
- Fedora 31, 30, 29
- Red Hat Enterprise Linux 8.1, 7.7, 6.10
- SUSE Linux Enterprise Server 15 SP1, 12 SP4, 11 SP4
- Debian GNU/Linux 10.2, 9.11, 8.11
- Ubuntu 19.10, 19.04, 18.04.3 LTS, 16.04.6 LTS, 14.04.6 LTS
- CentOS 8.0, 7.7, 6.10
- ALT Linux 9.0, 8.2 (no support for Wibu dongles)
- Amazon Linux AMI 2018.03
In addition, ABBYY offers professional services to adapt the software to other platforms.
Tested Cloud and virtual environments:
- Microsoft Azure Virtual Machines
- Amazon EC2
- Microsoft Hyper-V Server 2012 R2
- Microsoft Hyper-V Server 2016
- Oracle VM VirtualBox 5.2
- VMware ESXi 6.5
- VMware Workstation Player 12.5
- VMware Workstation Pro 14.0.0
- Linux KVM
ABBYY FineReader Engine can also be run in a Docker container on supported platforms.
ABBYY FineReader Engine Java wrapper has been tested on the following Java Development Kits:
- OpenJDK 13 x64
- OpenJDK 14 Early-Access (build 21) x64
- Oracle Java SE Development Kit 8u231 x64
- Oracle Java SE Development Kit 11.0.5 (LTS) x64
- Oracle Java SE Development Kit 13.0.1 x64
Memory
- for processing one-page documents — minimum 400 MB RAM, recommended 1 GB RAM
- for processing multi-page documents — minimum 1 GB RAM, recommended 1,5 GB RAM
- for parallel processing — 450 MB RAM + 350 MB RAM for each core
- for parallel processing of documents in Arabic, Chinese, Japanese, or Korean languages — 750MB RAM + 850 MB RAM for each core
Hard disk space
- 2.150 MB for library installation
- 100 MB for program operation
- Additional 15 MB for every page when processing a multi-page document
Other requirements
- Tmpfs size — 4GB + 1GB*(cores number)
- Swap size — 4GB + 1GB*(cores number)
- ABBYY FineReader Engine supports the systemd init system
- For correct font detection, the fonts contained in documents should be installed.
Developing Tools
The ABBYY FineReader Engine for Linux provides C/C++ native API and a Java wrapper, therefore applications need to be written in C/C++ or Java.
Hardware
PC with Intel processor (x86) 1 GHz or higher.
Operating system
- macOS 10.13.x High Sierra
- macOS 10.14.x Mojave
- macOS 10.15.x Catalina
Memory
- for processing one-page documents — at least 400 MB RAM, 1 GB RAM recommended
- for processing multi-page documents — at least 1 GB RAM, 1,5 GB RAM recommended
Hard disk space
2150 MB of free space for library installation and 100 MB for program operation, plus additional 15MB for every page, when processing a multi-page document.
For correct font detection, the fonts contained in documents should be installed.
Developing Tools
The Mac version provides only C/C++ native API, therefore applications need to be written in C/C++.
Supported recognition languages
ABBYY FineReader Engine 12 provides support for the highest number of recognition languages on the market. It offers recognition of languages with Latin, Cyrillic, Greek or Armenian characters, as well as Arabic, Burmese (technical preview), Farsi, Hebrew, Chinese, Japanese, Korean, Russian, Thai and other languages. To further increase the recognition accuracy, integrated dictionaries are provided for many languages. To increase recognition of unusual words and untypical fonts, a small integrated utility can be used for implementing own dictionaries and creating own character patterns.
In addition, the SDK provides recognition of historic documents printed between 17th and 19th century in English, French, German, Italian and Spanish, recognition of artificial languages (Esperanto, Interlingua, Ido and Occidental) recognition of programming languages (Basic, C/C++, COBOL, Fortran, JAVA, and Pascal), simple chemical formulas and standard digits.
× With dictionary support
* Arabic ICR is not supported. However, hand-printed Arabic digits can be recognized.
Languages for interaction with the user
Message boxes such as error messages, tips and warnings are available in English, Bulgarian, Czech, Chinese (PRC and Taiwan), Danish, Dutch, Estonian, French, German, Greek, Hungarian, Italian, Japanese, Korean, Polish, Portuguese (Brazil), Russian, Slovak, Spanish, Swedish, Turkish, and Ukrainian.
Supported Office input formats
ABBYY FineReader Engine can open documents created in the following formats:
- Text formats: .doc, .docx, .rtf, .htm / .html, .txt, .odt
- Table formats: .xls, .xlsx, .ods
- Presentation formats: .ppt, .pptx, .odp
- Digitally created PDFs: .pdf
Supported image formats (opening, saving)
ABBYY FineReader Engine can open image files in many formats. In addition, the OCR SDK is able to save results in several image formats.
List of supported image formats:
| Format | Extension | Open | Save |
|---|---|---|---|
|
BMP uncompressed black and white 4- and 8-bit — uncompressed Palette 16-bit — uncompressed, uncompressed Mask 24-bit — uncompressed 32-bit — uncompressed, uncompressed Mask |
bmp | ||
|
BMP 4- and 8-bit — RLE compressed Palette |
bmp | ||
|
DCX black and white 2-, 4- and 8-bit palette 24-bit color |
dcx | ||
|
DjVu (only in Windows version) black and white, gray, color |
djvu, djv | ||
|
GIF black and white — LZW-compressed 2-, 3-, 4-, 5-, 6-, 7-, 8-bit palette — LZW-compressed |
gif | ||
|
JBIG2 black and white |
jb2 | ||
|
JPEG gray, color |
jpg, jpeg, jfif | ||
|
JPEG 2000 gray — Part 1 color — Part 1 |
jp2, jpc, j2k | ||
|
PCX black and white 2-, 4- and 8-bit palette 24-bit color |
pcx | ||
| Image PDF (scanned PDF) | |||
| Digitally created PDF (Version 1.7 or earlier) | |||
|
PNG black and white, gray, color |
png | ||
|
TIFF black and white — uncompressed, CCITT3, CCITT4, Packbits, ZIP, LZW gray — uncompressed, Packbits, JPEG, ZIP, LZW 24-bit color — uncompressed, JPEG, ZIP, LZW 1-, 4-, 8-bit palette — uncompressed, Packbits, ZIP, LZW (including multi-page TIFF) |
tif, tiff | ||
|
TIFF black and white — CCITT3FAX |
tif, tiff | ||
|
WDP (only in Windows version) black and white, gray, color (WIC or Microsoft .NET Framework 3.0 required) |
Wdp | ||
|
WIC-compatible (only in Windows version) (WIC or Microsoft .NET Framework 3.0 required) |
Note: ABBYY FineReader Engine will not open images larger than 32512*32512 pixels.
Supported document saving formats
ABBYY FineReader Engine can save the recognized text in the following formats:
- RTF
- DOCX
- XLSX and XLS (only in Windows version)
FineReader Engine supports MS Excel 5 and 8 formats when saving to XLS format.
- PPTX
- PDF, PDF 2.0, PDF/UA
- PDF/A-1 (a,b), PDF/A-2 (a,b,u), PDF/A-3 (a,b,u)
FineReader Engine support MRC compression for all PDF formats.
- HTML, HTML 5
FineReader Engine supports various code pages (Windows, DOS, Mac, ISO) and Unicode (UTF-16, UTF-8) encoding
- TXT
FineReader Engine supports various code pages (Windows, DOS, Mac, ISO) and Unicode (UTF-16, UTF-8) encoding.
- CSV
- XML — file format contains recognized text which structure is described with the help of XML tags.
- ALTO 3.1
- XPS (only in Windows version)
- FB2
- EPUB
- ODT
- vCard — for export of business cards only
Supported barcode types
ABBYY FineReader Engine recognizes following types of barcodes:
- 1D: Codabar, Code 128, Code 39, Code 93, Code 32, EAN 8 and 13, Full ASCII Code 39, GS1-128, IATA 2 of 5, Industrial 2 of 5, Interleaved 2 of 5, Intelligent Mail (a.k.a USPS 4-CB), Matrix 2 of 5, Patch, PostNet, UPC-A, UPC-E.
- 2D: Aztec, Data Matrix, MaxiCode, PDF 417, QR Code.
Extraction of data from Machine Readable Zones (MRZ)
ABBYY FineReader Engine can detect a machine-readable zone on the image of an ID or travel document and extract data that is encoded in accordance with the ICAO Document 9303.
FineReader Engine will extract machine-readable data from both types of MRZ fields:
- 2 lines
- 3 lines
Additional information that can be extracted:
- Number of lines in MRZ
- All characters from each line
- Optional data from each line
- Type and subtype of ID document
- Number of ID document
- Code of issuing state
- Date of expiry
- Surname & All given names
- Nationality
- Date of birth & sex
- Personal number
Where available, the Engine extracts check digits of each value. To provide information about the quality of data extraction, it uses Boolean value that specifies whether the checksum over the individual value matches the check digit.
Optical mark recognition
ABBYY FineReader Engine recognizes simple checkmarks, grouped checkmarks, model checkmarks and checkmarks that were corrected by hand:
- Checkmarks in a square frame
- Checkmarks against the empty background
- Non-standard checkmarks (this type of checkmarks requires prior training)
For additional technical information, please refer to ABBYY.technology or consult the ABBYY FineReader Engine Help file.