ByteScout Text Recognition SDK – C# – Use Image Preprocessing Filters

Home
/
Articles
/
ByteScout Text Recognition SDK – C# – Use Image Preprocessing Filters

printable version:
ByteScout-Text-Recognition-SDK-C-sharp-Use-Image-Preprocessing-Filters.pdf

How to use image preprocessing filters in C# and ByteScout Text Recognition SDK

This code in C# shows how to use image preprocessing filters with this how to tutorial

The sample shows steps and algorithm of how to use image preprocessing filters and how to make it work in your C# application. ByteScout Text Recognition SDK is the software development kit for automatic text recognition and OCR from pdf documents and images. Can recognize English and non-English languages. It can use image preprocessing filters in C#.

Fast application programming interfaces of ByteScout Text Recognition SDK for C# plus the instruction and the code below will help you quickly learn how to use image preprocessing filters. In order to implement the functionality, you should copy and paste this code for C# below into your code editor with your app, compile and run your application. Test C# sample code examples whether they respond your needs and requirements for the project.

ByteScout free trial version is available for download from our website. It includes all these programming tutorials along with source code samples.

On-demand (REST Web API) version:
Web API (on-demand version)

On-premise offline SDK for Windows:
60 Day Free Trial (on-premise)

Program.cs

      using System;
using System.Diagnostics;
using ByteScout.TextRecognition;

namespace TextRecognitionExample
{
    class Program
    {
        static void Main(string[] args)
        {
            string inputDocument = @".\skewed.png";
            string outputDocument = @".\result.txt";

            // Create and activate TextRecognizer instance
            using (TextRecognizer textRecognizer = new TextRecognizer("demo", "demo"))
            {
                try
                {
                    // Load document (image or PDF)
                    textRecognizer.LoadDocument(inputDocument);

                    // Set the location of OCR language data files
                    textRecognizer.OCRLanguageDataFolder = @"c:\Program Files\ByteScout Text Recognition SDK\ocrdata_best\";

                    // Set OCR language.
                    // "eng" for english, "deu" for German, "fra" for French, "spa" for Spanish, etc. - according to files in "ocrdata" folder
                    // Find more language files at https://github.com/bytescout/ocrdata
                    textRecognizer.OCRLanguage = "eng"; 
                    

                    // Add deskew filter that automatically rotates the image to make the text horizontal.
                    // Note, it analyzes the left edge of scanned text. Any dark artifacts may prevent 
                    // the correct angle detection.
                    textRecognizer.ImagePreprocessingFilters.AddDeskew();

                    // Other filters that may be useful to improve recognition
                    // (note, the filters are applied in the order they were added):

                    // Improve image contrast.
                    //textRecognizer.ImagePreprocessingFilters.AddContrast();

                    // Apply gamma correction.
                    //textRecognizer.ImagePreprocessingFilters.AddGammaCorrection();

                    // Apply median filter. Helps to remove noise.
                    //textRecognizer.ImagePreprocessingFilters.AddMedian();

                    // Apply dilate filter. Helps to cure symbols erosion.
                    //textRecognizer.ImagePreprocessingFilters.AddDilate();

                    // Lines removers. Removing borders of some tables may improve the recognition.
                    //textRecognizer.ImagePreprocessingFilters.AddHorizontalLinesRemover();
                    //textRecognizer.ImagePreprocessingFilters.AddVerticalLinesRemover();

                    
                    // Recognize text from all pages and save it to file
                    textRecognizer.SaveText(outputDocument);

                    // Open the result file in default associated application (for demo purposes)
                    Process.Start(outputDocument);
                }
                catch (Exception exception)
                {
                    Console.WriteLine(exception);
                }
            }

//            Console.WriteLine();
//            Console.WriteLine("Press any key...");
//            Console.ReadKey();
        }
    }
}