The C# OCR Library

 OCR in 1 line of code
// NuGet PM> Install-Package IronOcr
using IronOcr;

string imageText = new IronTesseract().Read(@"images\image.png").Text;

 PDF OCR Text Extraction
using IronOcr;
using System;

var ocrTesseract = new IronTesseract();

using (var ocrInput = new OcrInput())
{
    // OCR entire document
    ocrInput.AddPdf("example.pdf", "password");

    // Alternatively OCR selected page numbers
    ocrInput.AddPdfPages("example.pdf", new[] { 1, 2, 3 }, "password");

    var ocrResult = ocrTesseract.Read(ocrInput);
    Console.WriteLine(ocrResult.Text);
}

 OCR with Barcode & QR Reading
using IronOcr;
using System;

var ocrTesseract = new IronTesseract();
ocrTesseract.Configuration.ReadBarCodes = true;
using (var ocrInput = new OcrInput(@"images\imageWithBarcode.png"))
{
    var ocrResult = ocrTesseract.Read(ocrInput);
    foreach (var barcode in ocrResult.Barcodes)
    {
        Console.WriteLine(barcode.Value);
    }
}

 125 International OCR Languages
//PM> Install-Package IronOcr.Languages.Arabic
using IronOcr;
using System;

var ocrTesseract = new IronTesseract();

ocrTesseract.Language = OcrLanguage.Arabic;

using (var ocrInput = new OcrInput(@"images\arabic.gif"))
{
    var ocrResult = ocrTesseract.Read(ocrInput);
    Console.WriteLine(ocrResult.Text);
}

// Example with a Custom Trained Font Being used:

var ocrTesseractCustomerLang = new IronTesseract();
ocrTesseractCustomerLang.UseCustomTesseractLanguageFile("custom_tesseract_files/custom.traineddata");
ocrTesseractCustomerLang.AddSecondaryLanguage(OcrLanguage.EnglishBest);

using (var ocrInput = new OcrInput(@"images\mixed-lang.pdf"))
{
    var ocrResult = ocrTesseractCustomerLang.Read(ocrInput);
    Console.WriteLine(ocrResult.Text);
}

 Fixing Low Quality Scans & Images
using IronOcr;
using System;

var ocrTesseract = new IronTesseract();
using (var ocrInput = new OcrInput(@"images\image.png"))
{
    ocrInput.Deskew();
    ocrInput.DeNoise();
    ocrInput.Despeckle();
    ocrInput.EnhanceResolution(225);
    ocrInput.Sharpen();
    ocrInput.Erode();
    ocrInput.Dilate();
    ocrInput.Scale(200);
    var ocrResult = ocrTesseract.Read(ocrInput);
    Console.WriteLine(ocrResult.Text);
}

 Fast OCR Configuration
using IronOcr;
using System;

var ocrTesseract = new IronTesseract();

// Fast Dictionary
ocrTesseract.Language = OcrLanguage.EnglishFast;

// Turn off unneeded options
ocrTesseract.Configuration.ReadBarCodes = false;
ocrTesseract.Configuration.RenderSearchablePdfsAndHocr = false;

// Assume text is laid out neatly in an orthogonal document
ocrTesseract.Configuration.PageSegmentationMode = TesseractPageSegmentationMode.Auto;

using (var ocrInput = new OcrInput(@"images\image.png"))
{
    var ocrResult = ocrTesseract.Read(ocrInput);
    Console.WriteLine(ocrResult.Text);
}

 OCR Image Optimization Filters
using IronOcr;
using System;

var ocrTesseract = new IronTesseract();
using (var ocrInput = new OcrInput(@"images\image.png"))
{
    // Note: You don't need all of them; most users only need Deskew() and occasionally DeNoise()
    ocrInput.WithTitle("My Document");
    ocrInput.Binarize();
    ocrInput.Contrast();
    ocrInput.Deskew();
    ocrInput.DeNoise();
    ocrInput.Despeckle();
    ocrInput.Dilate();
    ocrInput.EnhanceResolution(300);
    ocrInput.Invert();
    ocrInput.Rotate(90);
    ocrInput.Scale(150);
    ocrInput.Sharpen();
    ocrInput.ToGrayScale();
    ocrInput.Erode();

    // WIZARD - If you are unsure use the debug-wizard to test all combinations:
    string codeToRun = OcrInputFilterWizard.Run(@"images\image.png", out double confidence, ocrTesseract);
    Console.WriteLine(codeToRun);

    // Optional: Export modified images so you can view them.
    foreach (var page in ocrInput.Pages)
    {
        page.SaveAsImage($"filtered_{page.Index}.bmp");
    }

    var ocrResult = ocrTesseract.Read(ocrInput);
    Console.WriteLine(ocrResult.Text);
}

 OCR Image Color Editing
using IronOcr;
using IronSoftware.Drawing;
using System;

var ocrTesseract = new IronTesseract();

using (var ocrInput = new OcrInput("blue_and_pink.png"))
{
    ocrInput.WithTitle("Recolored");

    ocrInput.ReplaceColor(Color.Pink, Color.White, 10);
    // Pink detection has 10% tolerance

    ocrInput.ReplaceColor(Color.Blue, Color.Black, 5);
    // Blue detection has 5% tolerance

    // Export the modified image so you can manually inspect it.
    foreach (var page in ocrInput.Pages)
    {
        page.SaveAsImage($"black_and_white_page_{page.Index}.bmp");
    }

    var ocrResult = ocrTesseract.Read(ocrInput);
    Console.WriteLine(ocrResult.Text);
}

 OcrResult Class
using IronOcr;
using IronSoftware.Drawing;

// We can delve deep into OCR results as an object model of
// Pages, Barcodes, Paragraphs, Lines, Words and Characters
// This allows us to explore, export and draw OCR content using other APIs/
var ocrTesseract = new IronTesseract();

ocrTesseract.Configuration.ReadBarCodes = true;

using (var ocrInput = new OcrInput(@"example.tiff"))
{
    OcrResult ocrResult = ocrTesseract.Read(ocrInput);
    foreach (var page in ocrResult.Pages)
    {
        // Page object
        int PageNumber = page.PageNumber;
        string PageText = page.Text;
        int PageWordCount = page.WordCount;
        // null if we dont set Ocr.Configuration.ReadBarCodes = true;
        OcrResult.Barcode[] Barcodes = page.Barcodes;
        AnyBitmap PageImage = page.ToBitmap(ocrInput);
        int PageWidth = page.Width;
        int PageHeight = page.Height;
        double PageRotation = page.Rotation; // angular correction in degrees from OcrInput.Deskew()

        foreach (var paragraph in page.Paragraphs)
        {
            // Pages -> Paragraphs
            int ParagraphNumber = paragraph.ParagraphNumber;
            string ParagraphText = paragraph.Text;
            AnyBitmap ParagraphImage = paragraph.ToBitmap(ocrInput);
            int ParagraphX_location = paragraph.X;
            int ParagraphY_location = paragraph.Y;
            int ParagraphWidth = paragraph.Width;
            int ParagraphHeight = paragraph.Height;
            double ParagraphOcrAccuracy = paragraph.Confidence;
            OcrResult.TextFlow paragrapthText_direction = paragraph.TextDirection;
            foreach (var line in paragraph.Lines)
            {
                // Pages -> Paragraphs -> Lines
                int LineNumber = line.LineNumber;
                string LineText = line.Text;
                AnyBitmap LineImage = line.ToBitmap(ocrInput);
                int LineX_location = line.X;
                int LineY_location = line.Y;
                int LineWidth = line.Width;
                int LineHeight = line.Height;
                double LineOcrAccuracy = line.Confidence;
                double LineSkew = line.BaselineAngle;
                double LineOffset = line.BaselineOffset;
                foreach (var word in line.Words)
                {
                    // Pages -> Paragraphs -> Lines -> Words
                    int WordNumber = word.WordNumber;
                    string WordText = word.Text;
                    AnyBitmap WordImage = word.ToBitmap(ocrInput);
                    int WordX_location = word.X;
                    int WordY_location = word.Y;
                    int WordWidth = word.Width;
                    int WordHeight = word.Height;
                    double WordOcrAccuracy = word.Confidence;
                    foreach (var character in word.Characters)
                    {
                        // Pages -> Paragraphs -> Lines -> Words -> Characters
                        int CharacterNumber = character.CharacterNumber;
                        string CharacterText = character.Text;
                        AnyBitmap CharacterImage = character.ToBitmap(ocrInput);
                        int CharacterX_location = character.X;
                        int CharacterY_location = character.Y;
                        int CharacterWidth = character.Width;
                        int CharacterHeight = character.Height;
                        double CharacterOcrAccuracy = character.Confidence;
                        // Output alternative symbols choices and their probability.
                        // Very useful for spellchecking
                        OcrResult.Choice[] Choices = character.Choices;
                    }
                }
            }
        }
    }
}

 Create Searchable PDFs by OCR
using IronOcr;

var ocrTesseract = new IronTesseract();

using (var ocrInput = new OcrInput())
{
    ocrInput.AddImage(@"images\page1.png");
    ocrInput.AddImage(@"images\page2.bmp");
    ocrInput.AddImage(@"images\page3.tiff");

    ocrInput.Deskew();

    var ocrResult = ocrTesseract.Read(ocrInput);

    ocrResult.SaveAsSearchablePdf("searchable.pdf");
}

 Tesseract 5 for .NET
using IronOcr;
using System;

var ocrTesseract = new IronTesseract();

// This is done by default and can be omitted:
// ocrTesseract.Configuration.TesseractVersion = TesseractVersion.Tesseract5;

using (var ocrInput = new OcrInput(@"images\image.png"))
{
    var ocrResult = ocrTesseract.Read(ocrInput);
    Console.WriteLine(ocrResult.Text);
}

 Tesseract Detailed Configuration
using IronOcr;
using System;

var ocrTesseract = new IronTesseract()
{
    Language = OcrLanguage.EnglishBest,
    Configuration = new TesseractConfiguration()
    {
        ReadBarCodes = false,
        BlackListCharacters = "`ë|^",
        RenderSearchablePdfsAndHocr = true,
        PageSegmentationMode = TesseractPageSegmentationMode.AutoOsd,
    }
};

using (var ocrInput = new OcrInput(@"images\image.png"))
{
    var ocrResult = ocrTesseract.Read(ocrInput);
    Console.WriteLine(ocrResult.Text);
}

 OcrInput Class
using IronOcr;
using System;

var ocrTesseract = new IronTesseract();

using (var ocrInput = new OcrInput(@"images\image.png"))
{
    var ocrResult = ocrTesseract.Read(ocrInput);
    Console.WriteLine(ocrResult.Text);
}

 OCR a Region of an Image
using IronOcr;
using IronSoftware.Drawing;
using System;

var ocrTesseract = new IronTesseract();

using (var ocrInput = new OcrInput())
{
    // A 41% improvement on speed by specifiying a pixel region
    var ContentArea = new CropRectangle(x: 215, y: 1250, width: 1335, height: 280);
    ocrInput.AddImage("img/example.png", ContentArea);

    var ocrResult = ocrTesseract.Read(ocrInput);
    Console.WriteLine(ocrResult.Text);
}

 TIFF to Searchable PDF Converter
using IronOcr;

var ocrTesseract = new IronTesseract();

using (var ocrInput = new OcrInput())
{
    ocrInput.AddMultiFrameTiff("images/multiframe.tiff");

    var ocrResult = ocrTesseract.Read(ocrInput);

    ocrResult.SaveAsSearchablePdf("searchable.pdf");
}

 Image Resolution Optimization (DPI)
using IronOcr;
using System;

var ocrTesseract = new IronTesseract();

using (var ocrInput = new OcrInput(@"images\image.png"))
{
    ocrInput.TargetDPI = 300;

    var ocrResult = ocrTesseract.Read(ocrInput);
    Console.WriteLine(ocrResult.Text);
}

 MultithreadedTesseract OCR
using IronOcr;

var ocrTesseract = new IronTesseract();

using (var ocrInput = new OcrInput())
{
    ocrInput.AddPdf("scan.pdf");

    // Image processing is automatically multi-threaded
    ocrInput.Deskew();

    // OCR reading is automatically multi-threaded too
    var ocrResult = ocrTesseract.Read(ocrInput);
}

 OCR Progress and Performance Tracking
using IronOcr;
using System;


var ocrTesseract = new IronTesseract();

ocrTesseract.OcrProgress += (_, ocrProgressEventsArgs) =>
{
    Console.WriteLine(ocrProgressEventsArgs.ProgressPercent + "%   " + ocrProgressEventsArgs.Duration.TotalSeconds + "s");
};

using (var input = new OcrInput("large.pdf"))
{
    // Progress events will fire during the read operation even if the main thread is blocked.
    var result = ocrTesseract.Read(input);
}

 OCR for MultiPage TIFF Files
using IronOcr;
using System;

var ocrTesseract = new IronTesseract();

using (var ocrInput = new OcrInput())
{
    ocrInput.AddMultiFrameTiff("images/multiframe.tiff");

    var ocrResult = ocrTesseract.Read(ocrInput);
    Console.WriteLine(ocrResult.Text);
}

 Make any PDF have Searchable, Copyable Text
using IronOcr;

var ocrTesseract = new IronTesseract();

using (var ocrInput = new OcrInput())
{
    ocrInput.AddPdf("scan.pdf", "password");

    // Clean up twisted pages
    ocrInput.Deskew();

    var ocrResult = ocrTesseract.Read(ocrInput);
    ocrResult.SaveAsSearchablePdf("searchable.pdf");
}

 Using Custom Tesseract Language Files
using IronOcr;
using System;


var ocrTesseract = new IronTesseract();

ocrTesseract.UseCustomTesseractLanguageFile("custom_tesseract_files/custom.traineddata");

using (var ocrInput = new OcrInput(@"images\image.png"))
{
    var ocrResult = ocrTesseract.Read(ocrInput);
    Console.WriteLine(ocrResult.Text);
}

 Multiple Languages for 1 Document
//PM> Install-Package IronOcr.Languages.Arabic
//PM> Install-Package IronOcr.Languages.Chinese
using IronOcr;
using System;

var Ocr = new IronTesseract();

// Add a primary language (Default is English)
Ocr.Language = OcrLanguage.English;

// Add as many secondary languages as you like
Ocr.AddSecondaryLanguage(OcrLanguage.Arabic);
Ocr.AddSecondaryLanguage(OcrLanguage.ChineseSimplified);

using (var Input = new OcrInput(@"images\image.png"))
{
    var Result = Ocr.Read(Input);
    Console.WriteLine(Result.Text);
}

 Exporting Images of OCR Elements
using IronOcr;
using IronSoftware.Drawing;

var ocrTesseract = new IronTesseract();
using (var ocrInput = new OcrInput(@"images\image.png"))
{
    var ocrResult = ocrTesseract.Read(ocrInput);
    foreach (var page in ocrResult.Pages)
    {
        foreach (var word in page.Words)
        {
            word.ToBitmap(ocrInput).SaveAs($"page{page.PageNumber}_word{word.WordNumber}.png", AnyBitmap.ImageFormat.Png);
        }
    }
}

Case Studies

Name: C# OCR Library - IronOCR
Rating: 4.86 (101 reviews)

December 6, 2022

SanSaTek Testimonial

Sangkar Sari Teknologi is an international consultancy who are based in both Holland and Indonesia.

Ready to get started? Version: 2023.6 just released

View Licenses >