Full-text recognition (OCR)

Send Request Test Drive

Smart Document Engine OCR – full-text OCR system for desktop, server and mobile platforms that makes it easy to recognize and convert document images into text


Smart Document Engine OCR system employs cutting-edge artificial intelligence techniques to identify and convert text from images, whether they are photos or scans. The system has the capability to automatically detect and recognize printed text in more than 100 languages, including English and those with Latin alphabets, Arabic, Greek, Armenian, Chinese, Japanese and more, making it highly adaptable to diverse problem.


Developed by our team of scientists and engineers as part of our Green AI initiative, our GreenOCR® technology boasts speed and accuracy of recognition with minimal power consumption and environmental impact. The system can recognize up to 15 pages per second on the server without GPU, and can fully process an A4 sheet photo in just 3-4 seconds on a smartphone, while maintaining the highest level of accuracy.


Smart Document Engine can even recognize text on documents that have been folded or crumpled, making it a powerful tool for turning your smartphone into an instant scanner, replacing the need for traditional flatbed scanners.


Seamless integration

The Smart Document Engine is a remarkable tool that offers flexible integration of full-text recognition into your company’s current activities. The software (SDK) can be easily and conveniently integrated into existing business processes without disrupting the usual user experience. The solution is available for integration with a variety of information systems.

Send Request

What is the Smart Document Engine full-text recognition for?

Full-text recognition is crucial for document input for electronic document management systems, business process management systems, electronic archives, and RPA-systems.


With the Smart Document Engine’s high speed and accuracy in data extraction, you can elevate the automation of document processing to a whole new level.

How does full-text recognition work

Source image


Recognition results (per line)


  1. Smart Engines introduced OCR for text recognition in 102 languages at a speed of 15 pages per
  2. second
  3. Smart Engines scientists today announced a new generation of Smart Document Engine for instant and
  4. precise recognition of various documents and forms. The innovative system makes it possible to quickly
  5. scan the text documents and extract the necessary data using a mobile phone. Thus, Smart Engines has…

Functional Features Smart Document Engine OCR

1System provides the option for a preliminary search and rectification of the document image directly on the original image, whether it be a photo, scan, or other format
2In addition to providing string recognition results, system supplies the coordinates of text objects in the original image, as well as recognition confidence scores at the character, word, or string level
3System can be utilized to recognize text in the entire document image or in images of individual document fragments
4You don’t need any external services or resources because all calculations are done directly on the device that’s using the Smart Document Engine OCR. You can easily deploy it on-premise on a server, personal computer, as a standalone mobile application, or in a web application.
5System supports the recognition of input images in JPG, PNG, and TIFF formats. For documents in PDF and other formats, recognition is done after conversion to one of the supported bitmap data formats.
6You can package the image as a PDF/A format with embedded text information.

Private & Secure ID scanning software

Smart Engines software:


  • Runs 100% on-premise/on-device
  • High-level security standards of personal data processing — GDPR, CCPA, HIPAA
  • Compliance with regulatory requirements KYC in CIP and AML
  • Does NOT transfer the client’s data to third-party services and/or third parties for manual processing
  • Does NOT save or store it — the recognition process is performed in the local RAM of the device
  • Does NOT require internet access.

Advantages of Smart Document Engine full-text recognition

Smart Document Engine — a patented system that uses Artificial Intelligence (AI) for full-text recognition. With high speed and accuracy, it automatically recognizes and enters textual data from documents.
Pure AI and nothing more

Pure AI and nothing more

AI functions autonomously, without the need for cloud solutions (SaaS) or third-party services. It is private, secure, and works 100% on-device/on-premise.

Data recognition accuracy

Data recognition accuracy

No wasting time and money on employee errors with the latest high-precision GreenOCR®, developed by scientists of our company

High speed

High speed

On a 32-core HPC without a GPU, the full-text recognition speed reaches 15 pages per second

For multiple platforms and OS

For multiple platforms and OS

Windows, Linux, macOS, React Native, Flutter, Android, iOS, etc. on x86, x86_64, ARMv7-v8 (AArch32 and AArch64), MIPS (MIPS32 and MIPS64) CPU architectures

100+ languages

100+ languages

Recognizes text data in 100+ languages including Latin, Arabic, Armenian, Persian, Urdu, Japanese, Chinese, Korean, and others

No GPU required and easy to integrate

No GPU required and easy to integrate

The software (SDK) has a small footprint and doesn’t demand substantial computing resources or excessive memory usage. It seamlessly integrates into current business workflows without any complications.

Superior quality despite interference.

Superior quality despite interference.

Robust to capturing conditions such as camera angles, camera distortions, or lighting, and created to run on edge devices with unprecedented speed and quality

Test Drive our technologies

Try out Smart ID Engine technologies to scan ID cards, passports, driver’s licenses, visas, residence permits on photos and in a real-time video stream

What do we provide?

Smart Document Engine is delivered as an autonomous full-text recognition SDK (software development kit) which contains all the necessary precompiled libraries, programming interface documentation and integration examples for various programming languages. Developers are provided with a simple but multifunctional API (application programming interface), which allows to integrate the document recognition solution into the client’s software using languages C++, C#, Java, Python and Objective-C for a wide range of systems: iOS, Android, Linux, Windows, MacOS, etc. The following hardware platforms are supported: x86_64, ARM v7, v8 (Aarch32, Aarch64), MIPS. It is possible to connect to the popular RPA frameworks.


Smart Document Engine can be bundled with Smart ID Engine to provide functionality for entering ID documents data, the solution provides high quality and fast recognition of more than 2484 document types. Recognition of codified objects such as machine-readable zones (MRZ) and barcodes is available through the use of Smart Code Engine.

Technical Specification

  • x86
  • x86_64
  • ARMv7-v8 (AArch32 and AArch64)
  • MIPS (MIPS32 and MIPS64)
  • Android (5.1 and up)
  • iOS (10 and up)
  • Sailfish Mobile OS (2.2 and up)
  • Custom versions: upon request
  • MS Windows (all officially supported versions)
  • Linux kernel based OS, including Ubuntu, Red Hat (RHEL), Debian, CentOS, SUSE, Astra Linux, Oracle Linux, and others
  • macOS (all officially supported versions)
  • QNX (version 7.0 and up)
  • Solaris (version 11.3 and up)
  • Custom versions: upon request

Abkhaz, Afrikaans, Albanian, Armenian, Aymara, Azerbaijanian, Belarusian, Berber (Latin alphabet), Bosnian, Bulgarian, Cantonese, Castilian, Catalan, Chewa (Latin alphabet), Chibarwe (Latin alphabet), Chichewa (Latin alphabet), Comorian (Latin alphabet), Croatian, Czech, Danish, Dutch, English, Estonian, Fiji Hindi (Latin script), Fijian, Filipino, Finnish, French, Georgian, German, Greek, Haitian Creole, Hebrew, Hungarian, Icelandic, Indonesian, Irish, Italian, Japanese, Kazakh, Kinyarwanda, Kirundi, Korean, Kyrgyz, Latvian, Lithuanian, Luxembourgish, Macedonian, Malay (Latin alphabet), Maltese, Mandarin, Maori, Moldovan, Mongolian (Cyrillic alphabet), Nauruan, Ndau, Ndebele, Northern Sotho, Norwegian, Ossetian, Palauan, Polish, Portuguese, Quechua, Romanian, Russian, Serbian, Seychellois Creole, Shangani, Shona, Slovak, Slovene, Somali (Latin alphabet), Sotho, Southern Ndebele, Spanish, Swahili (Latin alphabet), Swazi, Swedish, Thai, Tajik, Tamazight (Latin alphabet), Tetum, Tok Pisin, Tonga, Tsonga, Tswana, Turkish, Turkmen, Ukrainian, Uzbek, Woleaian, Xhosa, Zulu.

  • Java (version 1.7 and higher)
  • Python (version 3.7.2 and higher)
  • C++ (standard C++ 11 and higher)
  • C (standard C99 and higher)
  • C# (version 6.0 and higher)
  • PHP (version 5 and higher)

Mobile SDK includes React Native and Flutter integration interfaces.

Integration with other programming languages and frameworks (such as Go, Perl, Xamarin, etc.) ​​is ensured by using the API in C

The SDK already contains examples of using Smart Document Engine in Java / Python / C++ / C / Swift / Objective C / C# / Java / PHP.

Send Request

Please fill out the form to get more information about the products,pricing and trial SDK for Android, iOS, Linux, Windows.

    Our customers

    2e Systems

    2e Systems use Smart Engines technologies in solutions for the airline industry.


    Raiffeisenbank scans identity documents using Smart Engines technologies

    BioCollections Worldwide

    BioCollections Worldwide speeds up patient data intake for COVID-19 testing with Smart Engines


    Sum&Substance, a global KYC/AML service provider, use Smart ID Engine for IDs scanning

    Send Request

    Please fill out the form to get more information about the products,pricing and trial SDK for Android, iOS, Linux, Windows.