Aspose.OCR-GPU 23.10.1

Optical character recognition (OCR) API for .NET

Product Page | Docs | Demos | API Reference | Examples | Blog | Search | Free Support | Temporary License

This package can be used to develop applications for on-premise operating systems and cloud platforms. You can build both 32-bit and 64-bit software, including ASP.NET, WCF, and WinForms.

Please note: our library implies the use of .NET programming languages, compatible with CLI infrastructure. If you require a corresponding native library for C++, you can download it from here.

API overview

Aspose.OCR for .NET can extract text from photos, scans, PDF documents and other graphical files. It allows you to add OCR functionality to a desktop or web application in less than 10 lines of code, without having to delve into complex mathematical operations, neural networks, and other technical details.

• Ready-to-use OCR engine with superior recognition speed and accuracy.
• Supports 27 languages based on Latin, Cyrillic and Asian scrips.
• Can work with rotated, distorted and noisy images.
• Supports most file formats you can get from a scanner or camera, as well as web links.
• Batch recognition of all images in a folder or archive.
• Recognizes the whole image or selected areas only; identifies words, lines or paragraphs.
• Recognition results are returned in the most popular document and data exchange formats.
• Spell checking of recognition results.
• Full compatibility with other Aspose products - build solutions of any complexity using familiar concepts with minimal code.

Recognition languages

Aspose.OCR can recognize a large number of languages and all popular writing scripts, including texts with mixed languages.

Extended Latin alphabet

• Croatian
• Czech
• Danish
• Dutch
• English
• Estonian
• Finnish
• French
• German
• Italian
• Latvian
• Lithuanian
• Norwegian
• Polish
• Portuguese
• Romanian
• Slovak
• Slovenian
• Spanish
• Swedish

Cyrillic alphabet

• Belorussian
• Bulgarian
• Kazakh
• Russian
• Serbian
• Ukrainian

Asian languages

• Chinese
• Hindi

Supported file formats

Aspose.OCR for .NET can recognize just about any file that you get from a scanner or camera, or download from the Internet:

• PDF
• JPEG
• PNG
• TIFF
• GIF
• BMP
• DjVu

Recognition results are returned in the most popular document and data exchange formats:

• Plain text
• HTML
• RTF
• Microsoft Word document
• Microsoft Excel spreadsheet
• Searchable PDF
• EPUB
• JSON
• XML

Get started

You can get familiar with Aspose.OCR for .NET by creating a minimal console application for extracting text from an image.

1. Create a new C# project in Visual Studio. You can use a very basic project template, such as Console App.
2. Install this NuGet package to the project.
3. Locate some image containing a line of text and save it to bin\Debug or bin\Debug\net6.0 directory of the project under the name source.png.
4. Create an instance of Aspose.OCR recognition engine in your Main method:

   Aspose.OCR.AsposeOcr recognitionEngine = new Aspose.OCR.AsposeOcr();
   

5. Add an image to OcrInput object:

   OcrInput input = new OcrInput(InputType.PNG);
   input.Add("source.png");
   

6. Extract text from the image:

   List<Aspose.OCR.RecognitionResult> results = recognitionEngine.Recognize(input, recognitionSettings);
   

7. Output the recognized text:

   Console.WriteLine(results[0].RecognitionText);
   

Full code:

Aspose.OCR.AsposeOcr recognitionEngine = new Aspose.OCR.AsposeOcr();
OcrInput input = new OcrInput(InputType.PNG);
input.Add("source.png");
List<Aspose.OCR.RecognitionResult> results = recognitionEngine.Recognize(input, recognitionSettings);
Console.WriteLine(results[0].RecognitionText);

Run the program. You will see the extracted text in the console output. If the text is too large, the result may be cut off due to trial restrictions. You can get a temporary license to remove all limitations of the trial version for 30 days.

Learn more

• Documentation
• API Reference
• Examples
• Blog
• Free Support Forum
• Paid Support Helpdesk