ByteScout Data Extraction Suite – C# – Check If OCR Is Required for PDF with PDF Extractor SDK

Home
/
Articles
/
ByteScout Data Extraction Suite – C# – Check If OCR Is Required for PDF with PDF Extractor SDK

printable version:
ByteScout-Data-Extraction-Suite-C-sharp-Check-If-OCR-Is-Required-for-PDF-with-PDF-Extractor-SDK.pdf

check if OCR is required for PDF with PDF extractor SDK in C# and ByteScout Data Extraction Suite

check if OCR is required for PDF with PDF extractor SDK in C#

The example source codes on this page will display you how to make check if OCR is required for PDF with PDF extractor SDK in C#. Check if OCR is required for PDF with PDF extractor SDK in C# can be applied with ByteScout Data Extraction Suite. ByteScout Data Extraction Suite is the bundle that includes three SDK tools for data extraction from PDF, scans, images and from spreadsheets: PDF Extractor SDK, Data Extraction SDK, Barcode Reader SDK.

C# code snippet like this for ByteScout Data Extraction Suite works best when you need to quickly implement check if OCR is required for PDF with PDF extractor SDK in your C# application. Follow the steps-by-step instructions from the scratch to work and copy and paste code for C# into your editor. Want to see how it works with your data then code testing will allow the function to be tested and work properly.

Trial version along with the source code samples for C# can be downloaded from our website

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 Bytescout.PDFExtractor;
using System;

namespace CheckIfOCRIsRequired
{
    class Program
    {
        static void Main(string[] args)
        {
            try
            {
                // Loop through all files in directory and check whether OCR operation is required
                foreach (string filePath in System.IO.Directory.GetFiles("InputFiles"))
                {
                    _CheckOCRRequired(filePath);
                }

            }
            catch (Exception ex)
            {
                Console.WriteLine("Error: " + ex.Message);
            }

			Console.WriteLine("Press enter key to exit...");
            Console.ReadLine();
        }

        
        /// <summary>
        /// Check whether OCR Operation is required
        /// </summary>
        /// <param name="filePath"></param>
        private static void _CheckOCRRequired(string filePath)
        {
            //Read all file content...
            using (TextExtractor extractor = new TextExtractor())
            {
                extractor.RegistrationKey = "demo";
                extractor.RegistrationName = "demo";

                // Load document
                extractor.LoadDocumentFromFile(filePath);
                Console.WriteLine("\n*******************\n\nFilePath: {0}", filePath);

                int pageIndex = 0;

                // Identify OCR operation is recommended for page
                if (extractor.IsOCRRecommendedForPage(pageIndex))
                {
                    Console.WriteLine("\nOCR Recommended: True");

                    // Enable Optical Character Recognition (OCR)
                    // in .Auto mode (SDK automatically checks if needs to use OCR or not)
                    extractor.OCRMode = OCRMode.Auto;

                    // Set the location of language data files
                    extractor.OCRLanguageDataFolder = @"c:\Program Files\Bytescout PDF Extractor SDK\ocrdata\";

                    // Set OCR language
                    extractor.OCRLanguage = "eng"; // "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

                    // Set PDF document rendering resolution
                    extractor.OCRResolution = 300;
                }
                else
                {
                    Console.WriteLine("\nOCR Recommended: False");
                }

                //Read all text
                var allExtractedText = extractor.GetText();
                Console.WriteLine("\nExtracted Text:\n{0}\n\n", allExtractedText);
            }

        }

    }
}