Smart Document Engine extracts and automatically enters data from a wide range of constituent, financial and accounting documents, as well as primary accounting documents. Automatic AI-based classification provides high-quality and fast identification of a document type, document segmentation, extraction of text and table details, marks, barcodes, as well as graphic details, such as logos, signatures, and stamps. The GreenOCR® optical character recognition technology is a high-quality solution for text recognition. The technology provides precise and fast recognition and minimizes AI’s carbon footprint.
Our developed AI is robust to various document forms and document details.The Smart Document Engine solution allows you to automatically enter data not only from fixed document forms, but also flexible forms (e.g, payment orders, pay slips, invoices) and semi- structured documents (charters, contracts, etc.). Automatic document classification and recognition are robust to various distortions which can occur with documents captured with a mobile phone camera: geometric distortions, brightness shifts, low resolution, poor focusing, radial distortion. Furthermore, our algorithms are robust to various scanning defects: skew, rotation, colour interpolation errors, damaged documents, and a damaged scanning surface. Thanks to this feature, the Smart Document Engine solution precisely and quickly recognizes charters, orders, invoices, balance sheets, financial performance reports and other documents both from scanned documents captured using ordinary office or specialized sheetfed scanners, and from photos captured on document cameras or regular mobile phones and tablets.
Smart Document Engine is an automated multi-purpose system for recognition of documents with flexible and fixed layouts. The system provides automatic data entry and verification of accounting, financial, constituent documents and company records with high speed and precision. The Smart Document Engine solution can be applied for automated data entry of primary accounting documents, financial reporting forms and payment documents to automate back-offices, as well as to facilitate client work at service points and during remote service provision. The solution provides recognition of accounting, constituent, and reporting documents for document management workflow. The Smart Document Engine form type classification module allows you to implement completeness verification, automate data entry into accounting systems, and create high-performance electronic document storage. The Smart Document Engine functionality includes the search for details in semi-structured documents, precise recognition of text details, tabular data analysis, search and recognition of marks (checkboxes), as well as analysis of handwritten notes. The software allows you to automatically enter and recognize documents and forms with a complex structure and perform cross-verification of data.
Thanks to the state-of-the-art methods of computer vision, machine learning, AI and careful optimization, the Smart Document Engine SDK allows to integrate the feature of scanning and recognizing accounting, constituent, and reporting documents in any application for mobile phones and tablets, office applications, integration buses, and data entry centers. The SDK does not heavily consume resources: scanning and recognition of a full-page balance sheet on a regular mobile phone takes about 2-3 seconds. Thus, a mobile phone turns into a high-performance document scanner and for high-quality recognition a regular 8-megapixel camera with autofocus is enough. The system performs automatic document detection, classification, and then an automatic location analysis of details and tables, OCR of typed fields, automatic ICR of hand-printed fields, OMR for labels and automatic 1D and 2D barcode recognition. The Smart Document Engine solution also provides a built-in tabular data processing module, as well as an extraction and verification module for graphic elements (such as stamps and signatures).
The Smart Document Engine system is an independent on-premises solution and does not transfer images to any third-party servers for processing and recognition, thus, sensitive data transfer to third parties is excluded. Consequently, Smart Document Engine is the most secure solution for both business and its customers. The Smart Document Engine SDK does NOT transfer data and images for processing to Smart Engines or to any third-party services, does NOT save data or images (the processing is carried out in the device’s local RAM) and does NOT require internet access. The Smart Document Engine SDK is GDPR, CCPA, HIPAA-compliant.
Smart Document Engine is delivered as an autonomous SDK (software development kit) to integrate it into the customer’s infrastructure and applications. The SDK includes OCR libraries compiled and optimized for a set of target platforms and operating systems, API documentation (application programming interface) and integration examples for various programming languages. The scanning and recognition API for constituent, accounting, financial documents, and company records allows you to integrate functionality into programs and applications built using C, C++, C#, Java, Python, PHP, Objective C and Swift. Optionally, the SDK can be bundled with the Smart ID Engine and Smart Code Engine systems to scan and recognize ID documents and codified objects using a unified software interface.
Thanks to a simple API, the Smart Document Engine SDK can turn iOS or Android OS phones into a scanner of accounting, constituent, reporting and payment documents, invoices, and other documents with fixed and flexible layouts. Our proprietary AI and computer vision algorithms provide high-speed (about 2 seconds per recognition of a full-size photo on iPhone XR) and autonomous document recognition not only in English, but also in other languages of the world.
Deep software and hardware optimization of the code and algorithmic recognition principles for various processor architectures allows Smart Document Engine to autonomously recognize accounting and constituent documents, records and other documents with fixed and flexible layouts on any personal computers (including nettops and all-in-one PCs), and turn them into high-performance workstations for entering and processing document images captured from various image capture devices (flatbed and sheetfed scanners, specialized document scanners and document cameras). A wide range of software interfaces provides the possibility of direct native integration into most information systems.
Thanks to thread safety and efficient resources management, the Smart Document Engine SDK allows you to implement scalable AI platforms for image processing of accounting, constituent, and primary accounting documents, as well as other documents with fixed and flexible layouts. The solution allows you to automate office workflows in small companies and large corporations. Unique algorithms for automatic document classification and localization in images (scans and photos) allow you to automatically process heterogeneous streams of input images. The recognition performance of complex data structured documents on modern computers (with an AMD Threadripper 3970X processor) is about 10 full-size photos per second, which allows our customers to create highly secure and efficient WebAPI services and integrate the SDK into existing data exchange buses.
Oman Arab Bank
Turkish Airlines uses Smart Engines’ ID scanning software
Please fill out the form to get more information about the products,
pricing and trial SDK for Android, iOS, Linux, Windows.