Powerful Royalty Free OCR SDK for .NET High performance, royalty-free C# .NET OCR recognition on Windows 32bit and 64bit. OCR SDK for .NET is an OCR library that allows developers to easily embed high-quality optical character recognition functionality in their products. OCR SDK for .NET is a 100% royalty-free SDK library for developers. As a result, our customers can enjoy the lowest total cost of ownership of a quality OCR system, which enables them to create more-competitive software products. OCR SDK for .NET offers a high performance API library for you to equip your C# .NET applications (Windows applications, Sliverlight, ASP.NET web service applications, ActiveX controls, etc.) with functionality of extracting text and position information from scanned documents. You can convert images (in various formats like JPEG, PNG, TIFF, PDF, etc.) into editable document formats (Text, Word, Excel, RTF, HTML, XML, searchable PDF, etc.). With this product, you can easily implement full document management solutions. Highlighted features of the OCR SDK for .NET include: Royalty-free distribution of the OCR runtime files with your software. No runtime licenses are required. Accurate OCR SDK - Powerful Royalty Free OCR library. OCR SDK to build C# OCR or VB.NET OCR Applications. Perform OCR on PDF documents. Support for JPG, JPEG, PNG, GIF, BMP, PCX, TGA, PBM, PNM, PPM and TIFF image file formats for OCR. Batch convert scanned PDF, TIFF and Image files (JPEG, JPG, PNG, BMP, GIF, PCX, TGA, PBM, PNM, PPM) to editable Word, Excel, CSV, HTML, TXT, Pure Text Layer PDF, Invisible Text Layer PDF, etc. formats. Supports 30+ languages: Bulgarian, Catalan, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, German, Hungarian, Indonesian, Italian, Latvian, Lithuanian, Norwegian, Polish, Portuguese, Romanian, Russian, Slovak, Slovenian, Spanish, Swedish, and Turkish, etc. Asian OCR module which supports 5 Asian languages: Chinese simplified, Chinese traditional, Arabic, Japanese, Korean. Able to apply different noise removal filters before image recognition. Read popular fonts including Arial, Times New Roman, Courier New, Verdana, Tahoma and Calibri. Support for regular, bold and italic font styles. Provide document cleanup functions. Base on an unique character analysis technology that can accurately recognize any fonts even in poor-quality images. Use advanced algorithms for analyzing poor-quality images, which may contain distorted, connected, and broken characters. Use dictionaries for the best recognition. Support multi-core CPUs to speed up recognition even of single text fragments through efficient parallel processing. Best Table Recovery Engine which can be used to recognize tables from scanned documents. Uses an advanced deskewing algorithm. Can detect misoriented pages (90/180/270 degrees rotation).
Source: http://www.e-pdfconverter.com/ocr-sdk-for-net/index.html