Ürünlerimize göz atın

If so you can download any of the below versions for testing. The product will function as normal except for an evaluation limitation. At the time of purchase we provide a license file via email that will allow the product to work in its full capacity. If you would also like an evaluation license to test without any restrictions for 30 days, please follow the directions provided here.

 

Net 22.6 için aspose.ocr

İndirmek  İndirmek 

Dosya Ayrıntıları

  • İndirmeks:
  • 1
  • Dosya boyutu:
  • 161.69MB
  • Ekleme Tarihi:
  • 30/6/2022

Tanım

Yeni denoising sinir ağı, tablo tanıma ve sistemi kaldır.

Dosya Ayrıntıları

Improved OCR Performance Support

Previously the System.Drawing was being used which has now been replaced with Aspose.Drawing. This has improved the OCR performance and cross-platform support.

Better Detection of Tabular Structures in OCR

A new DetectAreasMode enumeration has been introduced that allows to choose a neural network for the automatic detection of table cells. The available values are; NONE, DOCUMENT, PHOTO, COMBINE, TABLE. The TABLE value detects table cells with text via OCR API.

The following C# code snippet demonstrates how to detect image containing tabular content using API:

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-LICENSE.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);
        }
    }
}

New ML Model for Image Denoising in OCR

A new recognition setting has been introduced in the OCR API that you may enable or disable to perform automatic noise removal from the detected images. The specialized neural network removes dirt, glare, unwanted gradients, spots, noise, and scratches from the images.

Please note that we have implemented both the pre-processing and post-processing algorithms for Binarized Neural Network (BNN).

The following is a C# sample code to recognize image using automatics noise removal (denoising) via API:

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-LICENSE.lic");
            // Image path
            string image = "noisy.jpg";
            // Recognize
            RecognitioResult result = api.RecognizeImage(image, new RecognitionSettings {AutoDenoising = false});
            //Print recognition results
            Console.WriteLine(result.RecognitionText);
        }
    }
}

For a complete list of features, enhancements, and bug fixes in this release please visit, Aspose.OCR for .NET 22.6 - Sürüm notları.

 Türkçe