KEY FEATURES

Automatic image capture

Mobile Web Capture allows your customers to automatically capture images of documents using their mobile device to complete transactions using their mobile web browser without the need to physically snap a picture.

Automatic document detection

Because of the intuitive capabilities built into Mobile Web Capture, the software automatically detects the ideal time to capture an image best suitable for OCR.

Automatic pre-processing

Mobile Web Capture optimizes image quality by automatically detecting boundaries, cropping the document, correcting its perspective.

Enabling Content Intelligence

ABBYY Content Intelligence automatically makes customer information available to enterprise

KEY FEATURES

Point and capture

Automatically captures the best-quality image suitable for further back-end processing.

Automatic document detection

Automatically detects boundaries, crops the document, and corrects its perspective.

On-device OCR

Automatically recognizes text, either from a static image or from the camera preview screen, when the user simply points the camera at the document or object.

Customizable data capture

Extracts any specific data from a document by setting a regular expression describing the required content. Capture machine readable zones (MRZs) or international bank account numbers (IBANs) by simply applying predefined profiles.

Combining ABBYY’s latest AI-based technologies for information extraction with the highly scalable processing power of the Microsoft Azure computing infrastructure, this secure and reliable ABBYY cloud service can be easily integrated into your application via a REST API—empowering it to precisely convert virtually any number of pages within the shortest amount of time.

KEY FEATURES

Access to ABBYY recognition technologies in the cloud

ABBYY’s AI-based technologies for recognition of printed and hand-printed text (OCR and ICR), barcodes, and optical marks (OBR & OMR) accessible via Web API.

Capturing data from selected fields

Extracts data from pre-defined fields or utilizes ready-to-use data capture algorithms to capture data from business cards or machine-readable zones in ID documents.

Fast conversion into PDF

Highly scalable architecture for fast and accurate conversion of extensive document collections – from scans into searchable PDF or PDF/A files in minutes.

Easy integration via REST API

Access to the OCR web service from any part of the world via REST API, utilizing HTTPS POST and GET requests and receiving results in XML or JSON formats.

KEY FEATURES

Comprehensive set of recognition technologies

With OCR toolkit integration, applications can extract machine printed text in over 200 languages as well as hand printed text, optical marks and barcode values.

Powerful PDF processing tools

Versatile APIs allow processing many PDF types and converting scanned documents, TIFFs, JPEGs or image-only PDFs into different searchable PDF and PDF/A files.

Artificial Intelligence and Machine Learning

AI, ML and other advanced technologies provide outstanding recognition accuracy for multi-language documents and deliver searchable and editable documents that reflect their originals.

Multi-core CPUs, Cloud and Virtual Machines support

Support for document processing in parallel threads on multi-core CPUs, deployment in the cloud and virtual environments guarantees fast, flexible and scalable processing.

FlexiCapture Cloud enables organizations to accelerate digital transformation by complementing their automation systems with new and advanced cognitive capabilities that liberate the intelligence locked in their documents.

SCENARIOS

Process documents in the cloud

An intuitive user interface allows users to process documents directly with the ABBYY cloud application.

• Customer configures and controls processing settings via a FlexiCapture project.
• Service runs in the cloud.
• Documents come either from scanning/mobile app or from email.
• Results delivery and data set synch either rely on standard ready-to-run connectors or are developed by a partner.

Deliver service through REST API

ABBYY FlexiCapture Cloud supports a RESTful API enabling partners, integrators, ISVs and customers to easily consume production capture services as part of their applications and solutions.

• FlexiCapture Cloud API allows users to consume capture services from existing cloud applications.
• FlexiCapture Cloud learns from processing and improves results for all end customers.
• REST API enables import, export, and data set synchronization.

FlexiCapture SDK, as a delivery option of the FlexiCapture platform, provides developers with a powerful and flexible toolkit to smoothly integrate ABBYY’s industry-leading data capture technologies to empower their own products and services according to vertical market needs.

KEY FEATURES

Data capture for all document types

ABBYY FlexiCapture SDK provides tools for extracting data from fixed forms and from semi-structured and unstructured documents. All required data can be quickly located and extracted in an appropriate format.

Advanced document classification

Build-in document classification allows developers to create the classifier from scratch, train the classifier based on verification results, and implement learning by feedback to improve classification accuracy results.

Out-of-the-box invoice, receipt, and PO processing

FlexiCapture SDK provides ready-to-implement projects for invoice, purchase orders and receipt processing. Main fields are extracted out of the box, without the need for any additional configuration.

Learning by feedback

FlexiCapture SDK allows developers to implement training for field extraction and classification processes. Based on feedback provided by the end user, this technology dramatically improves accuracy of field extraction and classification.

API-based setup

FlexiCapture API allows developers to set up processing from scratch without using visual tools. For instance, they can create a blank project, then create the document definition, process and train the system, or they can build their own tools for administration of FlexiCapture projects.

Intelligent data extraction

Natural Language Processing (NLP) technology automates the identification and extraction of content from unstructured documents like contracts, leases, emails, and correspondence. By leveraging NLP, you can now automate the extraction of data from complex documents along with structured and semi-structured documents, helping to accelerate transactions while significantly reducing operating costs and errors.