Link Search Menu Expand Document

Correction to Deal with Date Issue after OCR - C#

PDF Extractor SDK sample in C# demonstrating ‘Correction to Deal with Date Issue after OCR’

Program.cs
using System.Diagnostics;
using Bytescout.PDFExtractor;

// This example demonstrates the use of Optical Character Recognition (OCR) 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 ScannedDocumentToText
{
    class Program
    {
        static void Main(string[] args)
        {
            // Create Bytescout.PDFExtractor.TextExtractor instance
            TextExtractor extractor = new TextExtractor();
            extractor.RegistrationName = "demo";
            extractor.RegistrationKey = "demo";

            // Load sample scanned document
            extractor.LoadDocumentFromFile("InvoiceWithNoise.png");

            // 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 https://github.com/bytescout/ocrdata
            
            // Set PDF document rendering resolution
            extractor.OCRResolution = 300;

            // Add profiles to fix issues with date.
            // To deal with wrong V in dates you can use a regular expression. The following will replace only V characters which are located between numbers:
            extractor.LoadProfiles("profiles.json");
            extractor.Profiles = "ocr-dateIssue";

             // Save extracted text to file
            extractor.SaveTextToFile("output.txt");

            // Cleanup
            extractor.Dispose();

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

profiles.json
{
  "profiles": [
    {
      "ocr-dateIssue": {
        "OCRCorrections.Add()": [ "(\\d)V(\\d)", "$1\\/$2", true ]
      }
    }
  ]
}

Download Source Code (.zip)

Return to the previous page Explore PDF Extractor SDK


Copyright © 2016 - 2021 ByteScout