Aspose.OCR-GPU NuGet Package

Aspose.OCR for .NET is a powerful yet easy-to-use and cost-effective API for extracting text from scanned images, photos, screenshots, PDF documents, and other files.

It allows you to add optical character recognition (OCR) functionality to your .NET desktop or web application in less than 10 lines of code without worrying about complex formulas, neural networks and other technical details.
Advanced machine learning models and artificial intelligence allow you to read text in 26 languages based on Latin and Cyrillic scripts, as well as Chinese. Various pre-processing filters allow you to correct rotated and noisy images without loss of recognition accuracy. To further improve recognition results, you can turn on spell checker, which finds and automatically corrects spelling errors.
Aspose.OCR can recognize scanned images or even smartphone photos in the most popular formats: PDF, JPG, TIFF, PNG, BMP, GIF, or DjVu. You can also perform batch image recognition from a folder or ZIP archive in one call.

The recognition results are returned in the most popular document and data exchange formats: plain text, PDF, Word, Excel, JSON and XML and can be further parsed and analyzed programmatically.
The library is fully compatible with other Aspose products. You can build solutions of any complexity using familiar concepts with minimal code.

Changelog

- Improved text overlay matching to the original image.

DEPRECATION WARNING:
Several classes and methods from previous versions of Aspose.OCR remain functional but are marked deprecated.
They will be removed in release 23.11.0 (November 2023) in favor of the new API introduced in this release.
Please adapt your code to replace them with the new APIs before then.

See the Release Notes for more details.

Check for details at https://docs.aspose.com/ocr/net/aspose-ocr-for-net-23-10-1-release-notes/

Resources:

Online documentation: https://docs.aspose.com/ocr/net/
Free support forum: https://forum.aspose.com/c/ocr/.