Pegasus Imaging Corporation
Accusoft Pegasus

my cart
purchase
download
contact us

imaging SDKs that accelerate development
ImageGear for .NET

.NET WinForms, ASP.NET and WPF imaging SDK

Scanning and compression
Viewing, annotation, and printing
Image editing and processing
Comprehensive OCR capabilities
Plus PDF and vector support

.NET 32/64-bit | Winforms | ASP.NET | WPF

OCR for ImageGear

Language Support

  • Includes support for over 100 different languages
  • Recognizes characters from multiple languages within a single image
  • For a complete list of supported languages please see our product documentation


Zone Based Processing

Auto-Zoning:
  • An automatic page layout decomposition process that breaks image into individual zones for processing.
  • Located Zones are assigned a type based on expected content: Flow, Table, Graphic.
  • Improves recognition results by removing image areas of the image from the valid processing area
  • Advanced Table detection improves data result reconstruction.
User Defined Zones:
  • Process an entire image or just the section containing the information you need.
  • Zones can be defined on the fly by a user, loaded from a file, or detected automatically by the engine.
  • Flexible API gives developers the ability to define areas of images to be processed and the type of content located in that defined area.
  • Apply advanced Data Checking zone by zone
  • Specialized content? Define the appropriate recognition module for your content.
Data Checking

  • A complete Checking Subsystem used to improve recognition accuracy.
  • Advanced spell checking using 17 different language dictionaries is provided. Each dictionary contains between 100,000 to 200,000 entries.
  • Vertical dictionaries improve spell checking and OCR accuracy for Medical and Legal industries.
  • Customize validation to your needs by defining User Dictionaries, with values specific to your needs
  • Validate results using Regular Expressions
  • Developers can use event based checking to start validation work flow.


Image Pre-Processing

  • Advanced Image Processing methods are available to improve OCR accuracy.
  • For highest accuracy the OCR engines looks for dark characters on a pale background. Auto Inversion functionality detects if the image needs to be inverted for highest accuracy.
  • Images getting scanned upside down? Processing landscape documents? Automatic image orientation detects and adjusts images so they are properly oriented.
  • Deskew methods will detect image misalignment and automatically correct it, improving auto-zoning and recognition accuracy.
  • Despeckling methods remove minor dots and imperfections in the image capture process.
  • Resolution enhancement can be performed to improve the quality of the low resolution images.
OCR Result Processing

Recognition Details:
  • Each character is returned with an accuracy Confidence Value.
  • One incorrect character can drastically change a word; for this reason the recognition engine reports a certainty value for all recognized words.
  • Advanced font information and location information allows ImageGear to create text representations of the original, with a similar layout.
Language Control
  • The ImageGear OCR engine processes all data in a Unicode format. The data output can be formatted for a specific code page.
Output to File
  • Image over PDF
  • Text based PDF
  • Microsoft Office 2007
  • Microsoft Office 97 (Word, Excel & Powerpoint)
  • RTF
  • HTML
  • XML
  • For a complete list of output formats please see the product documentation



Editions

The ImageGear for .NET OCR functionality is available in two different editions for distribution, Standard and Plus. The primary difference between these two versions is the list of output formats created by the OCR engine.

Standard Edition:
The PDF formatting in the Standard Edition is accomplished using text output reported by the OCR engine and ImageGear’s internal PDF engine.

Standard Edition Output Formats:
  • Searchable text PDF files
  • Text documents

Plus Edition:
Formatted output is created by using all of the recognition information (font detail, located image areas, and recognized table structure information) to reconstruct a representation of the original document. The Plus Edition leverages the power of the OCR engine to create the robust formatted output.

Plus Edition Output Formats:
  • Searchable text PDF files
  • Text documents
  • Word
  • Excel
  • HTML
  • and more
See product documentation for full details.


 
Click Here To Send Us Your Questions