We create complete trust and identity protection in any network related transaction ! Government issued documents like passports, driving licenses and national IDs determine your identity and used for identity verification while they remain in your safe custody (not in a remote server!). Any digitally stored identity object such as documents or biometric information are constantly under threat of getting stolen by hackers. Biometric data once stolen is difficult to replace. The new Smart Engine gold standard OCR Software solutions (SDKs) perform on-device ID validation and automated information capture on any mobile and web device at super fast speeds with complete data privacy and security. The best way to do digital identity proofing and strong customer authentication.

Smart ID Engine— accurate and eco-friendly AI-powered scanner for ID cards, passports, drivers licenses.

Smart ID Engine is a comprehensive AI tool for automatic ID scanning encopassing: fraud detection, ID document authentication with face and liveness verification of over 1974 types of ID documents from 210 issuing authorities worldwide. Our template driven 'Green' AI-based ID scanner technology automatically identifies the type of scanned IDs, then uses our industrial-grade eco-friendly OCR engine to recognize and extract all forms of  data  in 100+ languages, including barcodes, facial information and signature from the ID. At the same time, our specially developed computational document forensic AI carefully analyzes all aspects of the presented ID in the scanning process to prevent presentation attacks and spoofing attempts, analyzes the ID template security features, and captured data from the document, to detect fake ID scanning and other fraud attempts.

The software supports scanning of national ID cards, residence permits, international passports, drivers licenses, visas, and other travel and residence-related documents issued by countries of the European Union, South, Central, and North America, Australia, Oceania, and New Zealand, Middle and the Far East countries, Asian countries, and Africa. With our ID scanner app SDK for Android and iOS (iPhone, iPad),web,desktop, and server applications you can easily add an on-premise ID scanner for your company applications. Our ID scanning software is specially designed to work in all capturing conditions such as camera angles, camera distortions, or lighting, and is created to run on edge devices with unprecedented speed and quality.

All Smart Engine modules, run as a sub-routine in apps on-premise/on-device and does NOT transfer the client’s data to third-party services or external back-office manual processing, does NOT save or store it — thanks to our powerful template checking technology the verification process is performed in the local RAM of the device, without any data exchange. 

Smart Code Engine is a fast, precise and secure software solution for automated scanning and data extraction from bank cards, 1D and 2D barcodes, MRZ and other codified objects in photos, scans and real-time video stream.

Smart Code Engine is an SDK for authenticating and extracting data from bank cards; 1D and 2D barcodes (QR codes, AZTEC, PDF417, DataMatrix, EAN, UPC and others); MRZ codes on ID cards, passports, visas; vehicle license plates; as well as for, scanning price tags, labels and VIN numbers. The solution performs data recognition from single images (scans, photos) or  in a real-time video stream. Smart Code Engine has a small code footprint and can be used on devices with limited processing power, including smartphones, tablets, mobile terminals (e.g. cash registers), thin clients, as well as on any kind of servers and PCs.

The SDK works perfectly in poor lighting conditions and quick on-the-go scanning. The user does not need to focus on the image and hold a smartphone at a certain angle during recognition. The AI-based software does everything autonomously and automatically. The recognition process is performed only on the user’s device and on-premises. As in all Smart Engine modules, no external data exchange is necessary to complete the processing. Extraced data is used according to the programming of the main application within which the sub-routine will run. The technology fully complies with the requirements of the international law (GDPR, CCPA) in the field of personal data processing.

Smart Document Engine - automatic analysis and data extraction from business documents for desktop, server and mobile platforms.

Smart Document Engine is a high-performance software for automatic classification, recognition and analysis of documents and forms. The system helps to automate document management workflows and optimize data entry processes. Smart Document Engine quickly and securely scans and extracts the required data from various document types — standard and reporting forms, primary, business, statutory, financial, notarial, legal, insurance and banking documents, as well as standard questionnaires and forms with strict and controlled accountability.

Again, like the other Smart Engines products, Smart Document Engine works autonomously – data is NOT transferred to external servers, is NOT saved or stored and internet access is NOT required. The document recognition process is performed on the user’s device.

Thanks to our energy efficient GreenOCR® text recognition state-of-the-art technology and computer vision algorithms developed by our scientists and engineers, incorporating compact deep neural network architecture and the Hough transform (HoughNet and HoughEncoder) , Smart Document Engine solves business document recognition tasks even on mobile phones. With the Smart Engines software, a modern mobile phone can scan a document stream just like a specialized document scanner with a capacity of up to 30 pages per minute, previously possible only with high-performance workstations or servers. At the same time, there is no compromise on quality and the solution ensures the best text recognition, digital and other document data accuracy. The recognition of a full-page tax certificate on Galaxy S10 takes less than 3 seconds. The system performs quickly and precisely all the actions necessary for classification, data extraction and text recognition, robust to lighting conditions, geometric distortions and poor image quality.

The most important feature of Smart Document Engine is the ability to create customised solutions for automatic processing, classification, recognition and analysis of documents and forms of various complexities. Our high performance document recognition solutions help organizations to reduce costs and ease the processing workload without compromising data security as no transfer of document images are necessary to complete the tasks.

The GreenOCR® technology included in Smart Document Engine can accurately recognise printed texts (OCR), handprinted and handwritten form fields (ICR), as well as label and checkmarks (OMR). The implemented AI-based approach “I extract what I see” does not use linguistic models and is based on character recognition. producing a higher level of accuracy. 

Developers are provided with a simple API to integrate Smart Document Engine into the main software programs, with support for various programming languages such as C, C++, C#, Java, Python, PHP, Swift, Objective C for a wide range of operating systems: iOS, Android, Sailfish Mobile, Linux, Windows, macOS, Astra Linux, Atlix OS, etc. It is also possible to connect with popular RPA frameworks.

Privacy& Data Protection

Our offline capture technology means that all processing happens only on the user device. Personal Data is NOT transmitted, NOT stored, Internet access is NOT required, and data processing is performed in the RAM. This “rule of three NOTs” ensures a high security level for our clients. This is confirmed by an independent international audit.


Powered by proprietory GreenOCR algorithms

Developed in keeping with the responsible AI doctrine  initiative, our GreenOCR technology provides superior recognition quality and speed with minimal power consumption and environmental impact.

 We bring values to our customers while reducing the carbon footprint.

Fast, Secure & Accurate

Our proprietory 4-bit and 8-bit deep neural networking architecture  produces lightweight and robust computer vision software.

We decode information designed for machine recognition with exceptional precision and speed. The use of computational geometry, anytime algorithms, and hash codes to store templates  results in secure and autonomous recognition and verification even in low light or excessive light conditions and at any camera angle.