Table of Contents
ABBYY OCR & NLP
This site is a source of technical information about ABBYY technologies and toolkits for Optical Character Recognition (OCR), classification, data extraction and advanced language technologies.
Latest News & Info
Real-Time Recognition SDK 1 - Release 7 available (05.03.2018)
Key new features:
- Discrete data capture functionality extension with several additional ID documents
- Product's documentation enhancement
FineReader Engine 11 for Linux - Release 8 Update 3 available (27.02.2018)
Key new features:
- Support of multi-threaded solutions using C++.
- A new code sample ‘Multithreading’ for easy and fast development of a multi-threaded client-server application.
FineReader Engine 11 for Windows - Release 8 Update 4 available (16.01.2018)
This is a maintenance release containing bug fixes.
Real-Time Recognition SDK Cordova plugin available (11.12.2018)
... more details
FineReader Engine 11 for Linux - Release 8 Update 2 available (26.10.2017)
Key new features:
- RMI-capable Java Wrapper
- A new set of code samples for RMI-capable Java Wrapper
Real-Time Recognition SDK 1 - Release 6 available (26.10.2017)
Key new features:
- Support of new type of Singapore ID card
- Code samples in Swift 4
Real-Time Recognition SDK 1 - Release 5 available (11.08.2017)
Key new features:
- Support of Data Capture Interfaces
- IBAN Capture
- MRZ Capture
FlexiCapture Engine 11 - Release 3 Update 4 available (08.08.2017)
This is a maintenance release containing bug fixes.
FineReader Engine 11 for Windows - Release 8 Update 3 available (08.08.2017)
This is a maintenance release containing bug fixes.
Mobile Imaging SDK - Release 5 available (03.08.2017)
- The new release supports now ARM64 processors.
Real-Time Recognition SDK 1 - Release 4 available (06.07.2017)
Key new features:
- Ability to store patterns and dictionaries outside of the application's package/bundle
- [Technical preview] Data Capture support
FineReader Engine 11 for Mac - Release 8 available (28.04.2017)
This is a maintenance release containing a lot of new features and improvements:
- Extended method of injecting text into PDF.
- Ability to detect text layer in PDFs imported from memory stream.
- Faster printing of PDF using MRC.
Recommended Reading
Intelligent Classification
- Server-based classification to assign unstructured documents to its categories
- Supports TXT, Office, HTML, XML, PDFs, Images, others…
- No rules, based on Machine Learning
- Easy to train via intuitive, web based model editor
- Auto-algorithm optimization
- Integration via REST API
OCR Engine
- Scanning, Image Preprocessing, Multi-language Text-Recognition, PDF Processing, …
Learn more about the available OCR Features - Developers can integrate the technology in own applications or use it as an OCR Service
Text to Facts
- Information extraction technology based on natural language processing (NLP)
- InfoExtractor SDK reveals entities, events and relations across them
- Based on ABBYY's Compreno syntactic & semantic analysis platform