Link Search Menu Expand Document

OCR Analyser - C#

PDF Extractor SDK sample in C# demonstrating ‘OCR Analyser’

using System;
using System.Drawing;
using System.Diagnostics;
using Bytescout.PDFExtractor;

// This example demonstrates the use of OCR Analyser - a tooling class for analysis of scanned documents
// in PDF or raster image formats to find best parameters for Optical Character Recognition (OCR) that
// provide highest recognition quality.

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

namespace OCRAnalyser
    class Program
        static void Main(string[] args)
            // Input document
            string inputDocument = @".\sample_ocr.pdf";
            // Document page index
            int pageIndex = 0;
            // Area of the document page to perform the analysis (optional).
            // RectangleF.Empty means the full page.
            RectangleF rectangle = RectangleF.Empty; // new RectangleF(100, 50, 350, 250);

            // Location of language data files
            string ocrLanguageDataFolder = @"c:\Program Files\Bytescout PDF Extractor SDK\ocrdata_best\";

            // OCR language
            string 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

            // Create OCRAnalyzer instance and activate it with your registration information
            using (OCRAnalyzer ocrAnalyzer = new OCRAnalyzer("demo", "demo"))
                // Display analysis progress
                ocrAnalyzer.ProgressChanged += (object sender, string message, double progress, ref bool cancel) =>

                // Load document to OCRAnalyzer

                // Setup OCRAnalyzer
                ocrAnalyzer.OCRLanguage = ocrLanguage;
                ocrAnalyzer.OCRLanguageDataFolder = ocrLanguageDataFolder;
                // Set page area for analysis (optional)
                // Perform analysis and get results
                OCRAnalysisResults analysisResults = ocrAnalyzer.AnalyzeByOCRConfidence(pageIndex);

                // Now extract the text using detected OCR parameters

                string outputDocument = @".\result.txt";
                // Create TextExtractor instance
                using (TextExtractor textExtractor = new TextExtractor("demo", "demo"))
                    // Load document to TextExtractor

                    // Setup TextExtractor
                    textExtractor.OCRMode = OCRMode.Auto;
                    textExtractor.OCRLanguageDataFolder = ocrLanguageDataFolder;
                    textExtractor.OCRLanguage = ocrLanguage;

                    // Apply analysis results to TextExtractor instance
                    ocrAnalyzer.ApplyResults(analysisResults, textExtractor);

                    // Set extraction area (optional)

                    // Save extracted text to file

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

Download Source Code (.zip)

Return to the previous page Explore PDF Extractor SDK