ABBYY OCR & NLP

This site is a source of technical information about ABBYY technologies and toolkits for Optical Character Recognition (OCR) and advanced language technologies.

Latest News & Info

Semantics Conference Banner

  • The annual SEMANTiCS conference is the meeting place for professionals who make semantic computing work.
  • ABBYY will also present a session on: How to compute semantic relationships between entities and facts out of natural texts.
    • The talk covers how facts and their relationships that are relevant to an organization can be detected when combining deep linguistic analysis, a universal semantic hierarchy, artificial intelligence and domain-specific knowledge; for example in contract management scenarios.

Mobile OCR SDK icon Mobile OCR Engine 4.0 - Release 15 available (20.07.2016)

  • Upgrade of libpng version according to Google Play Policy requirements.
  • Bug fixes.
  • iOS: Download (Login needed)
  • Android: Download (Login needed)

Mobile Imaging SDK Icon Mobile Imaging SDK 1 - Release 4 Update available (08.07.2016)

  • Upgrade of libpng version according to Google Play Policy requirements.
  • more detailsDownload (Login needed)

FineReader Engine icon Receipt Capture SDK 1 - Release 1 available (21.06.2016)
This is the first release of ABBYY Receipt Capture SDK 1. Key features and benefits:

  • Easy-to-integrate SDK automatically extracting data from receipts.
  • For providers of Customer Loyalty Management software and services.
  • Extraction of basic fields, extended fields and line items.
  • Pre-trainied for 100+ USA top retail chains, can be easily trained via API.
  • more detailsDownload (Login needed)

Mobile OCR SDK icon Mobile OCR Engine 4.0 - Release 15 available (19.05.2016)

  • This maintenance release contains Android library for ARM-v7 and x86 processor architectures, improvements in Japanese OCR and bug fixes.
  • iOS: Download (Login needed)
  • Android: Download (Login needed)

OCR SDK icon FineReader Engine 11 for Windows - Release 7 Update available (25.05.2016)
This is a maintenance release containing a lot of new features and improvements:

  • Ability to convert documents containing undefined number of pages to searchable PDFs.
  • Simultaneous usage of network and standalone licenses within one installation.
  • Garbage removal from color images.
  • ... more detailsDownload (Login needed)

News Archive

Recommended Reading

Smart Classifier Logo

  • New server-based classification appliance, that allows classifying unstructured content into predefined categories.
    • Smart Classifier supports many file formats natively: TXT, Office, HTML, XML, PDFs, Images, others…
    • The system learns the characteristics of the specific document class based on the content of (= Machine Learning). No rules, works for all kind of unstructured documents.
    • Content experts can train and maintain the models via a modern, web based model editor
    • Smart Classifier's built in artificial intelligence selects and optimizes the algorithms to deliver high quality results
    • Integration via REST API
  • Agent ABBYY: A New World Order
    Watch Episode 1 and share it if you like it …
    ... watch the movie

FineReader Engine 11 Logo


InfoExtractor 2.0 logo

  • ABBYY InfoExtractor is an information extraction technology based on natural language processing (NLP)
  • InfoExtractor SDK reveals entities, events and relations across unstructured texts
  • ABBYY InfoExtractor is based on ABBYY's Compreno syntactic & semantic analysis platform

Selected Articles

© 2016 ABBYY. All rights reserved.

Recent changes RSS feed Driven by DokuWiki