Download Overview - FineReader Engine 12 for Windows

Latest Release

FineReader Engine 12 Windows - Release 4 Update 3 (8 September 2020)

More info and download of the latest release:
FineReader Engine 12 for Windows
– Login needed

Free download of the latest distributive is available for ABBYY customers with a valid Software Maintenance Agreement.
Please contact your Account Manager for login information.

New Features and Improvements in Release 4 and its updates

  • New: 'Compare Documents' Module
    • The new 'Compare Documents' Module in ABBYY FineReader Engine provides your software with the ability to quickly and accurately compare two versions of the same document and detect possible differences in their content – for example to compare the originally created contract and its printed and signed version and automatically verify the document’s integrity >
    • The technology can analyze documents in different formats, i.e. Microsoft Word, PDF, JPEG, TIF and other document or image formats and can provide significant value to any document processing solution, especially to applications for the legal, government and business sector.

  • In the Update 1 of the Release 4, the detection of changes in documents that contain text areas on pages as well text areas within tables was further improved.
  • In the Update 2 of the Release 4 the functionality of the 'Compare Documents' Module was further enhanced by adding several options that allow to further optimize the accuracy of the comparison results.
  • In the Update 3 of the Release 4, the functionality of the 'Compare Documents' Module was further enhanced by introducing a new approach for comparing specific bi-lingual documents with the translated text in a separate column. In this type of documents, such as international contracts, the text and its translated version are typically arranged in two parallel columns. To increase the precision of the comparison algorithm, a new option in the ‘Compare Documents’ module of ABBYY FineReader Engine provides the ability to compare each column (and thus each language version) separately. The new approach reduces the number of 'false positives' in such type of documents and leads to significantly higher precision of the comparison results.
  • Higher accuracy for Arabic OCR: New AI-based algorithms
    • Arabic OCR: Significantly improved recognition on low quality images
    • To increase recognition accuracy on low-quality images, new smart AI-based algorithms were implemented for recognition of Arabic. In addition to the ‘standard’ OCR processing approach, a newly trained Recurrent Neural Network for Arabic enables End-to-End recognition processes delivering highly accurate recognition results – even on images with very low quality. To optimize recognition quality and processing speed, a new intelligent built-in classifier selects the appropriate processing methodology.
  • Higher accuracy for Korean OCR: New AI-based algorithms
    • Korean OCR: Significantly higher recognition accuracy
    • To further increase the recognition accuracy of the Korean language, a new Deep Learning Language model was trained on a large document amount. This intelligent model selects the best recognition variant from different recognition hypotheses based on his ‘knowledge’ acquired during an extensive training on documents in Korean. To optimize the balance between the recognition accuracy and OCR processing speed, a new smart built-in classifier selects the usage of this new model only under specific conditions
  • New: Additional 1D barcode types (Update 2)
  • Three new 1D types of barcodes were added to the broad portfolio of supported barcodes:
    • KIX barcode
    • Royal Mail 4-State barcode (RM4SCC)
    • Australia Post 4-State barcode
  • Enhanced: Text-based classifier with advanced security of training data
    • To further increase the security and protection of information contained in training documents for the text-based classification , hashing algorithms were implemented. Using information from checksums eliminates the possibility to recover information from the sample documents.
  • Enhanced: MRZ Recognition (Update 2, Update 3)
    • The MRZ recognition functionality was introduced in Release 3.
    • In the Update 2 of Release 4, a new option was added that allows saving recognition results from Machine Readable Zones with the coordinates of the original image or with the coordinates of the image that was pre-processed prior to the actual OCR step.
    • In the Update 3 of Release 4, a new option was added that allows to specify the accepted length of the MRZ line. This property can be used to improve the recognition results for the machine-readable zone in cropped or low-quality images where the part of the MRZ line or lines might get lost during the pre-processing step and thus not comply with the MRZ specifications (the missing compliancy would lead to receiving no recognition result from the MRZ area).
  • Enhanced recognition: New methods for customizing the recognition area (Update 3)
    • To allow customizing the recognition area, two new methods were added that allow adding or cutting out regions of specified size from the recognition blocks.
  • Enhanced recognition of capital letters (Update 3)
    • A new option to increase the recognition accuracy of letter case and separate detection of capital letters and small caps.
  • Faster processing of Office documents: New option to open Office files from memory (Update 3)
    • Processing of Office documents was introduced in the Release 3.
    • In the Update 3 of Release 4, two new methods were added that allow opening Microsoft Office and Apache OpenOffice files directly from memory. The resulting reduced time for the document import step helps to accelerate the overall document processing speed. In addition, the set of properties for non-image formats was extended to better represent the original input formats.
  • New: Faster iteration of the recognition results in Engine Pool scenario (Update 3)
    • To speed up the iteration of the recognition results, a new method was introduced to save time for internal communication and increase the overall processing speed in scenarios, where the FineReader Engine runs outside of the main process.
  • Enhanced: Classification Demo Sample - now with Office format documents
    • To reflect the FineReader Engine’s capability of processing Office documents in the classification process, the provided pre-compiled Demo Sample for classification was enhanced and allows now to display Office documents in the classification results (in addition to PDFs and image formats). Furthermore, the newly added sample documents can be used to test and demonstrate the classification capabilities.
  • Updated: Code Sample for Command-Line Interface (CLI) (Update 3)
    • With this code sample, developers can efficiently utilize the FineReader Engine libraries and integrate document processing capabilities in command-line-based applications.
    • The CommandLineInterface code sample has been extended with a new set of keys for multi-processing, document analysis, synthesis, export, and opening images.
    • The CLI code sample is a cross-platform since this release and includes a unified set of keys for the Windows and the Linux environments.
  • Improved: Document layout preservation
    • To improve the detection and recreation of document layout, a new 'single-column' document model was introduced that provides more exact detection and analysis of tables and charts and significantly improves the detection and recreation of document layout.
  • New: .NET Core wrapper (Update 3)
    • To increase the efficiency of development teams using containers for software development or deployment, the ABBYY FineReader Engine now offers a new pre-built .NET wrapper based on .Net Core 3.1. (For: Windows, Linux)
  • Enhanced: Java wrapper (Update 2)
    • The Java wrapper was enhanced to improve the security of the system.
  • Enhanced: Java wrapper documentation
    • To simplify the usage of the API, the documentation of the ABBYY FineReader Engine 12 has been extended and the documentation for the Java wrapper is now provided in JavaDoc format in addition to the HTML and PDF formats.
  • Enhanced PDF file processing in multithreading environment (Update 2)
    • A new option for PDF processing was added to increase adds stability of PDF file processing.
  • Enhanced export formats (Update 3)
    • PDF
      • New options allow specifying the page orientation during the export to the PDF format in dependence on the selected paper size, setting up the most frequent page orientation used in the document, and in addition, it is now possible to combine PDF/UA and PDF/A-1/2/3-bu standards during the export to the PDF format.
    • Excel
      • Ability to set up image compression parameters during the export.
    • DOCX
      • Ability to automatically increase the page size if the content does not fit on the page, to customize page margins and to specify page margins in twipsin the output file.
  • Support of additional LibreOffice versions (Update 3)
    • ABBYY FineReader Engine 12 now supports following LibreOffice versions as input format for conversion of digitally created documents: 7.0, 6.1, 6.2, 6.3, 6.4
  • Updated Network License Manager (Update 2)
    • The Network License Manager for the Network and the Online licenses was updated to assure security of the system.
  • New code sample for document comparison
    • The extensive code samples library was extended by a new sample that allows testing and demonstrating the ability to compare two versions of the same document and detect differences in their content
  • Support of the latest .NET Framework versions
    • The distributive now includes .NET COM Interop wrappers for the .NET Framework versions 3.5, 4.0, 4.5, 4.6, 4.7, 4.8
  • New operating system support: Microsoft Windows Server 2019
    • FineReader Engine 12 Release 4 was tested on Windows Server 2019. This is the first release officially tested on this platform.
  • Improved: Developer's Help documentation
    • The Developer’s Help of the FineReader Engine 12 has been extended by additional information about different possibilities of licensing the SDK, describing the individual types of licensing options in an easy-to-understand comparison table.
    • In the Update 3 of Release 4, the article about about using ABBYY FineReader Engine in containers was enhanced with a scenario that assumes usage of two separate containers and multi-stage builds. In addition, extended information about usage of the Online license type was added to optimize the installation process.



  • GetEngine function was deprecated in R2 ⇒ To load the Engine object, please use the InitializeEngine function. It provides the unified Engine loading procedure for all license types (including the Online License).
  • Customers updating from previous versions of FineReader Engine such as version 9, 10, or 11 as well as upgrading from FineReader Engine 12 Release 1 to Release 2 and higher who use the GetEngine function would receive an error message if they keep using it in later releases. Please update your code and replace the GetEngine with the InitializeEngine function.
  • Important note about license name change: To better reflect its functionality, the license type ‘Cloud License’ was renamed into ‘Online License’ in the R3 for Windows. This license supports deployment in virtual & cloud environments, usage with Docker containers as well as on premise installations.

More details about individual features, fixed bugs and the latest release distributive can be found on the download page.

Previous Releases

Release 4 Update 2

FineReader Engine 12 Windows - Release 4 Update 2

  • Release date: 15.04.2020
  • Part #: 1342.60
  • Build #:

For functionality, please refer to the list of functions of Release 4 Update 3.

Release 4 Update 1

FineReader Engine 12 Windows - Release 4 Update 1

  • Release date: 4.12. 2019
  • Part #: 1342.47
  • Build #:

For functionality, please refer to the list of functions of Release 4 Update 2.

Release 4

FineReader Engine 12 Windows - Release 4

  • Release date: 28.10. 2019
  • Part #: 1342.44
  • Build #:

For functionality, please refer to the list of functions of Release 4 Update 1.

Release 3

FineReader Engine 12 Windows - Release 3

  • Release date: 04.06. 2019
  • Part #: 1342.37
  • Build #:
  • New input formats: Office documents
    • A new set of input formats was added to ABBYY FineReader Engine. In addition to image formats, the ABBYY FineReader Engine can now as well open and process the most common Office documents such as text documents, spreadsheets, and presentations:
      • Text documents: doc, docx, rtf, htm / html, txt, odt
      • Spreadsheets: xls, xlsx, ods
      • Presentations: ppt, pptx, odp

This new support of different types of input documents - scanned paper documents, different types of PDF, and digitally-born documents in Office formats - allows processing documents from multiple channels in a single flow.

  • Ability to extract information from MRZ in ID documents
    • Machine-readable zones (MRZ) are used in ID documents to encode personal information. With the ability to extract information from the machine-readable zone, FineReader Engine can be used in ID verification systems that are often used by government organizations as well as in solutions for customer onboarding used by employees of hotels, car rental companies, banks or insurance firms who need to quickly enter and verify their clients' personal data.
    • The personal information in machine-readable zone in ID documents is encoded as 2 or 3 lines of text according to specification of the ICAO Document 9303.
  • New OCR languages:
    • Georgian OCR: The Georgian language was added as a new OCR language
    • OCR for Simple Mathematical Formulas: ABBYY FineReader Engine now allows extracting characters of simple mathematical formulas. With the new OCR language Simple Mathematical Formulas it is possible to process scientific documents containing simple single-line mathematical formulas inside the text.
  • Enhanced OCR languages - with the support of Artificial Intelligence algorithms:
  • The newly trained Convolutional Neural Network for recognition of Asian languages provides following improvements:
    • Significantly faster recognition of Korean
    • Faster recognition of Chinese
    • Increased speed & accuracy in recognition of Japanese (Modern)
  • Enhancements in PDF export:
    • Extended set of tags on export to tagged PDF allows creating PDFs that are compliant with the Web Content Accessibility Guidelines in the European Union and the Section 508 Amendment to the Rehabilitation Act of 1973 in the USA.
    • Ability to save information about creation and editing dates during the export to PDF allows recording following information:
      • Date of creation
      • Date of modification
      • Both information (creation and modification dates)
  • Enhanced documentation
    • New article in product documentation describes how to deploy FineReader Engine in Docker containers.
    • EULA file is available in FineReader Engine files
  • Online License supporting proxy servers
    • The Cloud-based License was renamed into Online License. This type of license supports FineReader Engine's deployment in the Cloud. In addition, it allows using the FineReader Engine with Docker containers as well as deploying it within virtual environments. The Online License requires permanent internet connection. The licensing mechanism now supports proxy servers allowing to deploy FineReader Engine in systems with high security requirements, where the internet connection is allowed only via a proxy server.
  • Other improvements
    • Compatibility with latest Java releases allows to leverage modern development environments.
    • Ability to detect the build number of FineReader Engine before loading a java wrapper allows to check compatibility with host applications

Release 2 Patch 3

FineReader Engine 12 Windows - Release 2 Patch 3

  • Release date: 14.12.2018
  • Part #: 1342.18
  • Build #:

Improved availability of the cloud-based License Manager

The Release 2 Patch 3 offers highest availability of the cloud-based License Manager, which can be used with cloud OCR services, Docker containers or in virtual environments. In the Two-Server-Configuration, the License Manager resides on two licensing servers in Azure - one in Europe and one in the USA. In the improbable case of the main server's downtime, the license counter will be carried over to the back-up server.

Release 2 Patch 2

FineReader Engine 12 Windows - Release 2 Patch 2

  • Release date: 02.11.2018
  • Part #: 1342.16
  • Build #:

Release 2 Patch 1

  • Release Date: 29.10.2018
  • Part #: 1342.15
  • Build #:

Improved availability of ABBYY Cloud Licensing Server

When Cloud protected license is used, FRE connects to ABBYY Cloud Licensing server to synchronize a statistics of the product usage and to get a permission for work. If ABBYY Cloud Licensing server is not available, users will not be able to use a product.

To avoid such situations ABBYY has two Licensing Servers - one in Europe and one in the USA. In case European server is not available, FRE will connect to the US server. Two Licensing Servers configuration improves ABBYY Cloud Licensing Server availability.


  • API
    • IPE occurs on document analysis stage in case Greek language is used for recognition. ZD #145068
  • Recognition
    • On specific customer's document in Russian letter 'б' was recognized as digit '6'. ZD #134712
  • Barcodes
    • PDF417 barcode is not detected in parallel mode, though it is detected in sequential mode. HD #651022
  • Export
    • In case of export to ALTO, information about font family was not saved. ZD #135701
  • Visual components
    • IPE occurs in Visual Components if specific customer’s image is rotated using context menu in DocumentViewer. ZD #137190
    • Block's language is always set to default in case of loading FRDocument from a file. ZD #141550
  • Documentation
    • FRE does not detect both a beginning and the end of the word for CJK languages. All details about splitting text into words are described in the Help file. ZD #143735

Release 2

(Release 1 was not publically announced)

  • Release Date: 30.05.2018
  • Part #: 1342/12
  • Build #:
  • Improved classification
    • Advanced classification algorithms leverage modern machine learning and natural language processing technologies and offer improved document classification quality together with more flexible and fine-tuning options, new classification modes and improved classification API.
  • New deployment in Cloud
    • Cloud-enabled licensing allows integrating FineReader Engine in applications deployed within the Cloud environment (e.g. services as Amazon EC and Microsoft Azure) and using the SDK on workstations or virtual machines (containers)
  • New & improved OCR languages
    • IMPROVED: Japanese OCR accuracy - a new OCR language was added: Modern Japanese.
    • Farsi OCR - official support
    • Burmese OCR - technical preview
    • Japanese and Arabic documents: Enhanced recognition of dates, times, addresses and names when using new 'special predefined languages'
    • Improved recognition of right-to-left written languages: Two new properties help to detect the leftmost and the rightmost character in the word and to correctly designate the first and the last letters of the word during recognition and parsing.
  • Improved layout reconstruction
    • IMPROVED: Tables and layout reconstruction
    • Detection and recreation of balanced text columns
    • Dashed table borders on export to DOCX
    • Recreating cell borders color during the export to XLSX
    • Improved layout retention on TXT export
  • New export formats
    • Export in accordance with the latest PDF 2.0 standard as well as the PDF/UA standard support, new export formats: HTML 5 and ALTO 3.1.
  • New PDF/A saving options
    • PDF/A-2b and PDF/A-3b - new options for PDF/A-2 and for PDF/A-3 are supported for the level B conformance
  • New XML saving options and improvements
    • Faster export to XML, when saving information about character coordinates prior to image deskewing
    • Direct export of list elements to XML
    • Export an information about tab-space characters to XML
  • Other features and improvements
    • New scanning utility and options
    • New entity: Customer Project-ID decreases the numbers of errors during Engine object initialization.
    • Official support of Azure App Services
    • New HTML-based Help file
    • 256-bit AES encryption with the possibility to use Unicode characters during PDF encryption
    • Accessing information about individual recognition variants
This website uses cookies which enable you to see pages or use other functions of our websites. You can turn off such cookies in your browser’s settings. If you continue to use these pages, you consent to the use of cookies.
  • No tags, yet