Maximize performance and speed | C#ByteScout PDF Extractor SDK

Maximize performance and speed | C#


using System.Diagnostics;
using Bytescout.PDFExtractor;

// This example demonstrates the use of Optical Character Recognition (OCR) with "OCRMaximizeCPUUtilization" property to extract text 
// from scanned PDF documents and raster images.

// To make OCR work you should add the following references to your project:
// 'Bytescout.PDFExtractor.dll', 'Bytescout.PDFExtractor.OCRExtension.dll'.

namespace OCRExample
    class Program
        static void Main(string[] args)
            // Create Bytescout.PDFExtractor.TextExtractor instance
            TextExtractor extractor = new TextExtractor();
            extractor.RegistrationName = "demo";
            extractor.RegistrationKey = "demo";

            // Load sample PDF document

            // 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 OCR language data files
            extractor.OCRLanguageDataFolder = @"c:\Program Files\Bytescout PDF Extractor SDK\ocrdata_best\";

            // 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

            // Set PDF document rendering resolution
            extractor.OCRResolution = 300;

            // Enables max use of CPU and max use of multiple threads during OCR
            extractor.OCRMaximizeCPUUtilization = true;

            // Save extracted text to file

            // Cleanup

            // Open result document in default associated application (for demo purpose)
            ProcessStartInfo processStartInfo = new ProcessStartInfo("output.txt");
            processStartInfo.UseShellExecute = true;