You are here:: » TP » ABBYY OCR & NLP » Technology & Features
You are here:: » TP » ABBYY OCR & NLP » Technology & Features

Table of Contents

Overview OCR & PDF NLP, Linguistic & Semantic Comparisons Scenarios/Tasks Technology Cycles OS

Technology & Features

Features OCR

Optical Character Recognition consists of multiple different processing steps:
- Open & Load
- Image Preprocessing
- Document/Layout Analysis
- Character Recognition
- Verification
- Export

To get high quality results the different operations have to work seamlessly together. On the following pages you will find more details about the features and options in ABBYY's OCR technology:

More: OCR & PDF Features

Cross Product Topics

These topics are related to multiple product lines and technologies.

Linguistic/Semantic/NLP

ABBYY Compreno is a new set technologies that allows to analyze text in natural language.

  • The first product is based on the new NLP backend is ABBYY InfoExtractor.
  • InfoExtractor allows to to extract entities, facts and relationship between them from all kind of file formats.
  • Compreno technology innovates in many areas, so don't be surprised when you will hear about “ontologies” or “RDF/XML”
  • If you know ABBYY and its products/technologies - this is really new, innovative stuff ;-)

More: Linguistic Technologies

Scenarios

ABBYY SDKs and solutions solve very different “information access” problems. Here a short selection how the different features are used.

More: Scenarios/Tasks

Comparison

More: Comparisons

Technology Timeline

  • ABBYY introduced the core OCR technology to the market in back in 1993. The FineReader brand enabled computers to “read” text from images and is now well known worldwide.
  • The data capture technology under the FormReader/FlexiCapture brand allow to generated highly structured data from forms and semi-structured documents.
  • ABBYY's new Compreno technology now addresses the wide area of Natural Language Processing. The ultimate goal is to enable IT-systems to understand the semantic meaning of information hidden in unstructured documents written in natural language.
  • ABBYY brings its technologies to the market in different “flavors”. So they work perfectly for different user groups and usage scenarios. Almost all core technologies are available as
    • SDK for developers, software houses and enterprises so that they could enhance their product and systems
    • Solutions that are available through a value-adding reseller channel
    • Applications so that our professional users can increase their productivity with ABBYY's innovations

ABBYY Technologies from OCR to Data Capture to NLP