Collapse All Expand All

The ImageGear.Recognition namespace API offers a set of objects that provide access to document recognition technology. It enables you to build OCR applications for the Windows .NET development environment.

This core software module, referred to hereafter as the recognition engine, provides unsurpassed recognition accuracy for almost any document, including those produced on typewriters, dot-matrix printers, ink-jet printers, laser printers, and phototypesetters, as well as photocopied and faxed versions of any documents.

The figure below illustrates a simple application that takes a page image as input and produces recognized text in a variety of output formats.

 

This section provides information about the following:

• About the ImageGear Recognition API
• The ImageGear Recognition API and Multi-Threading
• Walkthrough: Multi-Threaded Recognition Using the .NET Parallel Class
• Working with the ImageGear Recognition API
• Error Handling
• Object Structure of the Recognition API
• Top-Level Object Lifetime and Disposal
• Importing Images into the Recognition API
• Preparing the Image for Recognition
• Pre-Processing the Image
• Pre-Processing Operations
• INVERSION
• DESKEWING
• ROTATION and MIRRORING
• DESPECKLING
• RESOLUTION ENHANCEMENT
• BLANK PAGE DETECTION
• Working with Zones
• Adding Zones
• Auto-Zoning
• Adding Zones Manually
• Adding Zones from a Zone File
• Detecting Tables without Visible Cell Separators
• Example: Defining a Zone Manually
• Example: Updating a Zone
• Recognition
• Recognition Modules
• The Recognition Process
• Recognizing a Multi-Page Document
• Recognizing a Single-Page Document
• Structured Data Output
• OCR Performance Considerations
• Defining the Character Set
• Recognition of a Bi-Lingual Document
• Character Set with No Language Selection
• Language Selection, LanguagesPlus Characters, and Local Filter
• Multiple Languages, Global and Local Filters, FilterPlus Characters
• Recognized Data Kept in Memory
• Checking
• Improving Accuracy with the Checking Subsystem
• Spell Checking
• UD-Checking
• User-Written Checking
• Applying Checking
• Spell Checking Languages
• Spell Checking with Automatic Spell Language Selection
• UD-Checking Prerequisites
• Preparing and Maintaining the User Dictionary
• Recognition Output
• Code Pages
• Exporting Recognized Data Directly to Text Formats
• Exporting to a PDF Output Document
• Exporting to a Formatted Output Document
• Format Retention in Final Output Documents
• Embedded Images in Final Output Documents
• Confidence Reporting
• Progress Indication
• Processing Statistics
• Distributing Recognition Engine Files with an Application
• Distributing Core Recognition Files
• Distributing Recognition Engine Files for the Western OCR Feature
• Distributing Recognition Engine Files for the Asian OCR Feature
• Distributing Recognition Engine Files for the Formatted Output Feature
• Recognition Namespace Specifications
• Characters and Code Pages
• Code Page List
• Customized Code Pages
• Code Page Ignored during Converting to the Output
• Output Text Format List
• Language Dictionary List
• Vertical Dictionary List
• Specifications for the Recognition Modules
• Filling Method - Recognition Module Combinations
• Recognition Modules and the Widest Available Character Set
• Recognition Modules and Filters
• Recognition Modules and Trade-off Settings
• Recognition Modules and the Checking Subsystem
• DOT 9-Pin Draft Dot-Matrix Recognition Module
• FRX Multi-Lingual Omnifont Recognition Module
• MOR Multi-Lingual Omnifont Recognition Module
• MTX Omnifont Recognition Module
• PLUS2W and PLUS3W Omnifont Recognition Modules
• Asian Recognition Module
• Migrating from ImageGear v16 Recognition
• API Elements Removed from ImageGear v17.3
• API Elements Added in ImageGear v17.3
• API Elements Modified in ImageGear v17.3
• Classes Declared as Sealed in ImageGear 17.3

 

 

---

©2014. Accusoft Corporation. All Rights Reserved.

Send Feedback