Please Try a Different Browser

You are using an outdated browser that is not compatible with our website content. For an optimal viewing experience, please upgrade to Microsoft Edge or view our site on a different browser.

If you choose to continue using this browser, content and functionality will be limited.

image1

The most robust OCR and imaging SDK for Linux

Add powerful imaging, OCR recognition and PDF capabilities to your most critical applications.

Overview

Scanning, OCR and PDF technologies for Linux

With advanced algorithms to take the guesswork out of getting great results from poor quality images, you’ll quickly realize why top Data Loss Prevention, Enterprise Content Management and Invoice Processing vendors choose the Tungsten OmniPage SDK. Here are a few more reasons they choose to work with us.
Attractive mature asian man with white stylish short beard looking at laptop computer with teenage eye glasses hipster woman in cafe. Teaching internet online or wifi technology in older man concept.

Increase productivity, lower costs and maximize ROI with the world’s most accurate OCR solution.

Take advantage of our years of Linux development expertise with access to a dedicated support team, tutorials and webinars.

Add document classification, form processing and extensive language support to your critical applications with add-on packages.

Features

Why customers choose OmniPage for Linux

Accurate OCR 

Delivers unmatched flexibility and accuracy with machine-print OCR (OCR, OCR-A, OCR-B and MICR), handprint (ICR), checkmark (OMR) and barcode (1D and 2D) recognition engines.

Versatile APIs

Easy-to-use APIs are available to build and control characteristics of the recognition and conversion processes. Supports C/C++ programming and is available in 64-bit version.

Output formats

Supports a wide range of image and application formats for outputting the conversion results, including BMP, GIF, TIF, PDF, HTML, Microsoft Office formats, RTF, TXT and XML.

PDF toolkit

Unique PDF overlay matching achieves up to 100% accuracy in PDF conversion significantly reducing development costs. Supports output to all PDF/A-1, -2, -3 levels for long-term document archival and can generate mixed raster content files optimized for file size and quality.

Forms processing

Offers capabilities for forms processing applications. Enables users to extract information from forms using predefined templates created with the Form Template Editor  (FTE)..

Language support

Supports more than 125 languages such as Latin, Greek and Cyrillic alphabets as well as Arabic, Hebrew, Chinese, Vietnamese, Japanese and Korean. Provides language detection capabilities for documents with multilingual content.

System requirements

Hardware and software:

  • Intel or AMD 64-bit CPUs

Tested operating systems:

  • Debian 8.8, 9.6
  • Ubuntu 14.04, 16.04 and 18.04
  • Fedora 28 and 29
  • CentOS 7.6
  • RedHat Enterprise Linux server 7.6
  • Oracle Linux 7.6
Related resources