Use ABCocr.NET to convert text to images...
ABCocr.NET is an Optical Character Recognition (OCR) component for the Microsoft .NET Framework. It's based around a custom version of Tesseract 3, an OCR engine, originally developed as a commercial product by Hewlett-Packard and has been extensively revised more recently with sponsorship from Google. Tesseract has proven to be one of the most accurate OCR engines available.
ABCocr.NET leverages the strength of Tesseract's accuracy, and additionally provides enhanced stability, support for both 32 and 64-bit Windows systems. ABCocr additionally supports multi-threading, so it's safe for use with multithread server environments and APIs like ASP.NET, or you can distribute the workload across multiple CPUs and cores!
Tesseract supports English, Spanish, French, German, Italian, Portuguese, Arabic, Bulgarian, Catalan, Chinese (simplified and traditional), Croatian, Czech, Danish (Fraktur script and standard), Dutch, Finnish, Greek, Hebrew, Hungarian, Indonesian, Japanese, Korean, Latvian, Lithuanian, Norwegian, Polish, Romanian, Russian, Serbian, Slovak (Fraktur script and standard), Slovenian, Swedish, Tagalog, Thai, Turkish, Ukrainian, and Vietnamese. Tesseract can also be trained to work in other languages.
Learning to perform OCR tasks from within .NET couldn't be easier. The documentation for ABCocr.NET is included with the distribution, and contains example code and simplified projects written for CSharp and VB.NET.
Like all our products, ABCocr.NET will work for the first thirty days uninterrupted, as a free trial period. If you wish to apply for a single free license, or need to purchase a license, please visit our website.
