Monday, July 10, 2017

Robust OCR Engine Implementation & Enhanced Characters Splitting Mechanism using .NET

What’s new in this release?

Aspose team is proud to announce the new release of Aspose.OCR for .NET 17.6.0.  The major development in this release is the improvements made to make processing of OCR operation more fast and robust. Implementation of the OCR engine has been upgraded in such way that neural network calls have been reduced. More OCR process classifier has been introduced and characters splitting mechanism is also improved in this release. Logic for setting up the spaces between the words has been improved. Characters splitting mechanism has been further improved and An improvement has been made in connecting the outlines splitter for recognizer. Since all the enhancements are internal to the API, there are no public API changes from end user’s point of view and the features can be used readily with this new version.  This release includes plenty of new features as listed below
  • hOCR for creation of the searchable PDF
  • Improved logic to set the spaces between the words
  • Clusterizator to reduce the number of calls to OCR and use the average images for OCR
  • Outlines and clustering splitters to separate touching letters
  • Words list for verification
Other most recent bug fixes are also included in this release

Overview: Aspose.OCR for .NET

Aspose.OCR for .NET is a character recognition component built to allow developers to add OCR functionality in their ASP .NET web applications, web services and Windows applications. It provides a simple set of classes for controlling character recognition tasks. It helps developers to work with image (BMP, TIFF) files from within their own applications. It allows developers to extract text from images quickly & easily, saving time & effort involved in developing an OCR solution from scratch.

More about Aspose.OCR for .NET

No comments:

Post a Comment