IronOCR is an advanced OCR (Optical Character Recognition) & Barcode library for C# and VB.Net.
The engine adds OCR functionality to Desktop, Console and Web applications in minutes. IronOCR reads Text, Barcodes & QR from all major image and PDF formats.
Language packs available for Arabic, Simplified Chinese, Traditional Chinese, Danish, English, Finnish, French, German, Hebrew, Italian, Japanese, Korean, Portuguese, Russian, Spanish, and Swedish at http://ironsoftware.com/csharp/ocr/ or as individual NuGet packages.
What makes IronOCR different is how well it deals with poor quality scans. IronOCR can read scans with low resolution, paper distortion and background noise. It takes the time to analyze the input file and prepare it for OCR to achieve consistent results every time.
Image pre-processing supports: Rotation & De-Skewing, Background Noise Cleaning, Resolution Enhancement, Increasing Contrast, Colour Simplification, and Setting Crop Regions.
IronOCR automatically detects the quality of an image before reading. Developers can adjust advanced image processing settings if needed.
Data output options include: Plain Text, Barcode Data, Object model structured data (headings, paragraphs, lines, words, and characters for each page).
Requires: .Net framework 4.0 or above on the Windows Platform including Cloud hosting such as Azure. Supports multithreading to improve OCR performance on multi-core servers.
Licensing & Support available for commercial deployments. For code examples, documentation & more visit http://ironsoftware.com/csharp/ocr/ For support please email us at firstname.lastname@example.org
- Digital PDF signing with images and encryption certificates (p12 / pfx).
- Improved support for OCR on specific crop regions within pages and documents.
- PDF OCR Reading improved for speed & stability
- PDF handling API extended with convenient method overloads
- Improved OCR accuracy, especially for skewed & low DPI scans and images
This package has no dependencies.