Aspose.OCR for .NET 22.6 - Release Notes

This article contains a summary of recent changes, enhancements and bug fixes in Aspose.OCR for .NET 22.6 (June 2022) release.

GPU version: 21.6.0

What was changed

Key	Summary	Category
OCRNET-465	Replaced System.Drawing with Aspose.Drawing to improve performance and cross-platform support.	Enhancement
OCRNET-513	Added a new detection mode for better identification and recognition of tabular structures.	Enhancement
OCRNET-517 OCRNET-535	Added a new machine learning model for image denoising: Integrated Binarized Neural Network (BNN) and related tests. Implemented pre- and post-processing algorithms for Binarized Neural Network.	New feature

Public API changes and backwards compatibility

This section lists all public API changes introduced in Aspose.OCR for .NET 22.6 that may affect the code of existing applications.

Added public APIs:

The following public APIs have been introduced in this release.

RecognitionSettings.AutoDenoising

A new recognition setting for enabling or disabling automatic noise removal from recognized images.

When enabled, images are pre-processed by a specialized neural network to remove dirt, spots, scratches, glare, unwanted gradients, and other noise. It consumes additional resources and is disabled by default.

DetectAreasMode.TABLE

A new DetectAreasMode value that allows to choose a neural network for the automatic detection of table cells.

Updated public APIs:

No changes.

Removed public APIs:

No changes.

Usage examples

The examples below illustrates the changes introduced in this release:

Recognize image with automatic noise removal

using Aspose.OCR;

namespace ProgramOCR
{
    class Program
    {
        static void Main(string[] args)
        {
            // Create instance of OCR API
            AsposeOcr api = new AsposeOcr();
            // Set license
            License lic = new License();
            lic.SetLicense("Aspose.Total.lic");
            // Image path
            string image = "noisy.jpg";
            // Recognize
            RecognitioResult result = api.RecognizeImage(image, new RecognitionSettings {AutoDenoising = false});
            //Print recognition results
            Console.WriteLine(result.RecognitionText);
        }
    }
}

Recognize image with tabular content

using Aspose.OCR;

namespace ProgramOCR
{
    class Program
    {
        static void Main(string[] args)
        {
            // Create instance of OCR API
            AsposeOcr api = new AsposeOcr();
            // Set license
            License lic = new License();
            lic.SetLicense("Aspose.Total.lic");
            // Image path
            string image = "table.jpg";
            // Recognize
            RecognitioResult resultTable = api.RecognizeImage(image, new RecognitionSettings {DetectAreasMode = DetectAreasMode.TABLE});
            //Print recognition results
            Console.WriteLine(resultTable.RecognitionText);
        }
    }
}