KB Overview Documentation Comparisons FAQ Tips & How to Command Generator Support

Comparisons overview

Here you will find some OCR technology comparisons between different ABBYY products and Open Source OCR projects.


The table below lists differences between the ABBYY CLI OCR for Linux with the alternative to use the ABBYY Cloud OCR service via Rest-API. Both approaches allow to automate the text recognition process via “light” coding, however the implementation is different.

Integration Integration on a terminal/script level REST-API
Coding Ready to use from the command line Custom Code required,
Code sample are available
Internet Connection only needed for CLI download & activation (http or email) required to upload the document images/PDFs and to download the results
Processing Processing on the local machine Remote processing,
ABBYY service running on Windows Azure
Scalability Local machine capacity limits,
use multiple licenses/machines to scale up
V11 comes with built in multi-core support
Auto-Scalability of the service,
well suited to process large projects
Cloud OCR Scalability
Feature Set Packaged Feature Set Packaged Feature Set
some features that are not available in the CLI, e.g. Business Card reading, Support of machine readable zones, Zonal OCR
Defined feature & volume packages Pre-Paid Volume (online or contract),
Subscription contracts
Trial online on ocr4Linux.com free Developer registration with free test images and a test volume for own documents,
Browser based test-tool to visually see the OCR result
License Activation activation of the CLI license on the local machine required service can be used from different machines,
no local license needed
Payment one time payment,
pay per use, pre-paid
Data Privacy local processing, security depends on the machine setup ABBYY Cloud OCR service is setup, running and following the European data privacy law.
The jobs and processing results can/have to be deleted.
Contractual Data Outsourcing agreements are available for large projects and integration of the service in other server/cloud back ends.

ABBYY CLI OCR vs. ABBYY FineReader Engine for Linux

  • ABBYY offers its OCR technologies on Linux as Command Line Tool but also as a full SDK:
    ABBYY FineReader Engine for Linux Technology Portal - abbyy.com
  • Technically the CLI OCR Tool is a code sample that is also provided with the SDK.
    The version that ABBYY offers online, has
    • installation routines
    • the options were fully tested

General Differences

CLI OCR OCR SDK - FineReader Engine
Usage Ready to use from the command line No ready to use application,
Coding needed (C/C++)
Integration Integration on a terminal/script level Real, deep integration into
existing applications
Feature set Limited feature set makes it easy to use The SDK allows to set up the processing
an recognition parameters
on a very granular level
Low Level
Access to the conversion results
“offline” in XML
SDK gives access to internal
OCR processing parameters and results
also “live” API to define recognition blocks
Defined feature & volume packages Possible to get customized
Runtime licenses (Volume, Add-Ons,
Standalone/ Network Licenses)
Trial Test ABBYY CLI OCR for Linux - free of charge 60 day 10.000 pages
available after signing a Trial Software license agreement
Investment No SDK investment Initial SDK costs
Operating Systems
Windows CLI Sample part of FineReader Engine
Windows, Linux,

Feature Differences

The table below lists some major feature/technical differences between the latest Linux CLI OCR tool and the corresponding SDK FineReader Engine 11 Linux. While the CLI Tool is designed mostly for document conversion, the SDK allows much more granular control for integration and processing.

CLI OCR OCR SDK - FineReader Engine
Bitness 32-Bit & 64-Bit 64-Bit
Im & Export only File Sytem File System & RAM
Document Classification not available new in Version 11
more on the ABBYY Technology Portal
Business Card Reading not available new in Version 11
more on the Technology Portal
Image Pre-Processing packaged in high level parameters
Image Processing Keys
granular control of the parameters via API
recommended for “tricky” images e.g. taken with cameras
Dictionary API not available possible to create own dictionaries via API
RAM Dictionaries
Old Font Recognition for Gothic/Fraktur available only for larger projects,
please contact ABBYY
available on request for the Developer license
project based licensing
Field Level / Zonal OCR not available yes
Java Integration Custom management for JVM - CLI tool communication Java Wrapper of the FRE API available
Licensing Standalone Standalone & Network licensing available
Defined feature & volume packages Possible to get customized
Runtime licenses
PDF/A-1 & PDF/A-2 Export yes yes
PDF/A-3 yes,
no attachment support

Open Source OCR or ABBYY Linux CLI

  • There are/were several Open Source OCR projects in the past and the most active one is probably Tesseract.
  • Optical character recognition (OCR) is not only about pure “character recognition”, but also about
    • supported image input formats and intelligent PDF processing
    • adjusted image pre-processing to get suitable characters for recognition separated form backgrounds as well as
      • good binarisation
      • straightened text lines
    • layout analysis to detect what is
      • text, a text column and the reading order
      • a table
      • an image
      • a barcode
    • support of different alphabets
      • e.g. Latin, Cyrillic, Greek, Hebrew, Arabic …
    • support of different print types
      • e.g. regular printed fonts, dot-matrix, typewriter,…
    • support of recognition languages
      • e.g, Character sets, dictionaries, …
    • export formats & options for
      • e.g. TXT, XML, PDF, Office Formats, HTML, ePUB
    • etc.
  • ABBYY is developing and improving the core technologies for all of the above mentioned areas for over 20 years.
    • To bring OCR technology to a new level of speed and quality a lot of scientific work and quality testing has to be made.
    • Ongoing testing is extremely important, because this is the only way that the complete package is getting better.
  • ABBYY products and technologies are used worldwide and millions of pages are processed every day. To be able to deliver this generic approach for a universal OCR technology a lot of scientific research in pattern recognition, linguistics and other IT know how has to be build up.
  • In daily OCR production environments a very broad variety of documents (file types, document layouts, fonts, languages, etc.) have to be processed. The OCR result has to be as good as possible - almost always after only one processing run.
    In this area a commercial OCR software probably is worth the investment, because the result of the recognition on most standard documents can be used right away. This statement is not against any of the open source projects, but as a matter of fact even the pre-compiled distributive would not be able to full fill this generic approach.
  • There are other scenarios, where a specially tuned Open Source OCR engine can deliver better results than the “out of the box ABBYY product”. This can happen on certain images or document types that were not part of the core production process.

Here some external URLs where multiple Open Source OCR Engines were tested.

  • Read the BLOG Article on splitbrain.org comparing: abbyyocr - cuneiform - gocr - ocrad - tesseract
    • Linux OCR Software Comparison - (5.2010)

Back to: