Aspose.OCR Cloud SDK for .NET

Aspose.OCR Cloud SDK for .NET

C# .NET REST API to Build OCR Applications

Make your own Optical Character Recognition (OCR) programs to recognize & English, Spanish & French text from raster images stored on the cloud.

Get Started
 

Aspose.OCR Cloud SDK for .NET Aspose.OCR Cloud SDK for .NET

Overview

  GitHub   Learn Buy
  
 

Aspose.OCR Cloud SDK for .NET assists .NET programmers to develop OCR processing and manipulation apps for cloud using their .NET supported language of choice (e.g., C#, ASP.NET etc.). Our OCR Cloud SDK is based on Aspose.OCR REST API and is offered under an MIT license.

Aspose.OCR Cloud SDK for .NET makes it very easy for .NET developers to perform OCR recognition operations on raster images (BMP, JPG, GIF, PNG, TIFF) in the cloud, extract text from raster images and export to TXT, PDF or OCR formats.

Aspose.OCR Cloud SDK for .NET enables your C# code to read font and character information of English, Spanish and French languages, return response in JSON and XP formats as well as extract the raster image text via OCR technology. You can scan and extract the whole image or provide X and Y coordinates of a specific section of the image to perform OCR operation on that particular section for text extraction.

Advanced OCR API Features

Extract and recognize text from images via OCR

Recognize text from whole or partial image

Specify portion of the image from which to extract text

Read character and font information from raster images

Return the response in XML or JSON format

Recognize English, French or Spanish text from image

Multi-platform support

We offer an on-demand OCR service. That means that you can start using our service at a minimum cost. Basically, it is OCR as a service. You can use any language and platform that supports HTTP to interact with our OCR API. However, manually writing client code can be difficult, error-prone and time-consuming. Therefore, we provide and support SDK packages in many development languages in order to make it easier to integrate with us. Our OCR SDK is implemented in .NET.

Automated document layout detection

Recognize documents with complex layouts in fully automatic mode or with manual corrections.
In automated mode, you don’t need to worry about text layout editing. Our automated document layout detection algorithm provides such functionality. Although, you can always manually correct (edit) the results of the automated detection of the text location from specific parts of an image. It allows performing the OCR operation quickly on document scans that follow a similar structure.

High speed with no resources

We use high-reliable and high-performance GPU-based Amazon servers to host our core, built on cutting edge fast neural networks.

Recognize Text of Different Languages

Aspose.OCR Cloud supports (various)(any)(all), fonts in regular, bold and italic text styles as well as multiple languages such as English, French, Italian, German, and Spanish, languages.

Supported image formats

*.bmp, *.dib *.jpeg, *.jpg, *.jpe *.jp2 *.png *.webp *.pbm, *.pgm, *.ppm *.pxm, *.pnm *.pfm *.sr, *.ras .tiff, *.tif *.exr *.hdr, *.pic

Various output formats

You can scan or photo your hard copies (papers, paper documents) and convert them to searchable PDFs or a simple Plain Text. You can convert the results to more complex formats using an hOCR output. You can convert the results to more complex formats using alternative structured data format “hOCR” , which allows developers to receive all content in the format of structured font styles, sizes, locations of Headings, Paragraphs, Lines.

Advanced Automative Image Pre-processing

Aspose.OCR Cloud can successfully read poor quality scans and automatically make image pre-processing to correct low resolution, low contrast, noise and skew. With as little as 3 lines of code, you can add OCR feature to your applications. OCR c# example:

    OcrApi api = new OcrApi();
    var request = new PostOcrFromUrlOrContentRequest(@”http://image.png”);
    OCRResponse response = api.PostOcrFromUrlOrContent(request);
  

Support and Learning Resources