Tesseract OCR in C#

Free for development. Licenses from $399

Examples

OCR in 1 line of code

// Nuget PM> Install Package IronOcr
using IronOcr;

var Result = new IronTesseract().Read(@"images\image.png").Text;

' Nuget PM> Install Package IronOcr
Imports IronOcr

Private Result = (New IronTesseract()).Read("images\image.png").Text

PDF OCR Text Extraction

using IronOcr;

var Ocr = new IronTesseract();


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

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

    var Result = Ocr.Read(Input);
    Console.WriteLine(Result.Text);
}

Imports IronOcr

Private Ocr = New IronTesseract()


Using Input = New OcrInput()
	' OCR entire document
	Input.AddPdf("example.pdf", "password")

	' Alternatively OCR selected page numbers
	Input.AddPdfPages("example.pdf", { 1, 2, 3 }, "password")

	Dim Result = Ocr.Read(Input)
	Console.WriteLine(Result.Text)
End Using

OCR with Barcode & QR Reading

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

Dim Ocr = New IronTesseract()
Ocr.Configuration.ReadBarCodes = True
Using Input = New OcrInput("images\imageWithBarcode.png")
	Dim Result = Ocr.Read(Input)
	For Each barcode In Result.Barcodes
		Console.WriteLine(barcode.Value)
	Next barcode
End Using

125 International OCR Languages

//PM> Install Package IronOcr.Languages.Arabic

using IronOcr;

var Ocr = new IronTesseract();
Ocr.Language = OcrLanguage.Arabic;

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


///A more advanced Example

var Ocr2 = new IronTesseract();
Ocr2.UseCustomTesseractLanguageFile("custom_tesseract_files/custom.traineddata");
Ocr2.AddSecondaryLanguage(OcrLanguage.EnglishBest);

using (var Input = new OcrInput(@"images\mixed-lang.pdf"))
{
    var Result = Ocr2.Read(Input);
    Console.WriteLine(Result.Text);
}

'PM> Install Package IronOcr.Languages.Arabic

Imports IronOcr

Private Ocr = New IronTesseract()
Ocr.Language = OcrLanguage.Arabic

Using Input = New OcrInput("images\arabic.gif")
	Dim Result = Ocr.Read(Input)
	Console.WriteLine(Result.Text)
End Using


'''A more advanced Example

Dim Ocr2 = New IronTesseract()
Ocr2.UseCustomTesseractLanguageFile("custom_tesseract_files/custom.traineddata")
Ocr2.AddSecondaryLanguage(OcrLanguage.EnglishBest)

Using Input = New OcrInput("images\mixed-lang.pdf")
	Dim Result = Ocr2.Read(Input)
	Console.WriteLine(Result.Text)
End Using

Fixing Low Quality Scans & Images

using IronOcr;

var Ocr = new IronTesseract();
using (var Input = new OcrInput(@"images\image.png"))
{
    Input.Deskew();
    // Input.DeNoise(); // only use if accuracy <97%
    var Result = Ocr.Read(Input);
    Console.WriteLine(Result.Text);
}

Imports IronOcr

Private Ocr = New IronTesseract()
Using Input = New OcrInput("images\image.png")
	Input.Deskew()
	' Input.DeNoise(); // only use if accuracy <97%
	Dim Result = Ocr.Read(Input)
	Console.WriteLine(Result.Text)
End Using

Fast OCR Configuration

var Ocr = new IronTesseract();

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

// Latest Engine 
Ocr.Configuration.TesseractVersion = TesseractVersion.Tesseract5;

//AI OCR only without font analysis
Ocr.Configuration.EngineMode = TesseractEngineMode.LstmOnly; 

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

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

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

Dim Ocr = New IronTesseract()

' Fast Dictionary
Ocr.Language = OcrLanguage.EnglishFast

' Latest Engine 
Ocr.Configuration.TesseractVersion = TesseractVersion.Tesseract5

'AI OCR only without font analysis
Ocr.Configuration.EngineMode = TesseractEngineMode.LstmOnly

'Turn off unneeded options
Ocr.Configuration.ReadBarCodes = False
Ocr.Configuration.RenderSearchablePdfsAndHocr = False

' Assume text is laid out neatly in an orthagonal document
Ocr.Configuration.PageSegmentationMode = TesseractPageSegmentationMode.Auto

Using Input = New OcrInput("images\image.png")
	Dim Result = Ocr.Read(Input)
	Console.WriteLine(Result.Text)
End Using

OCR Image Optimization Filters

using IronOcr;

var Ocr = new IronTesseract();
using (var Input = new OcrInput(@"images\image.png"))
{
    Input.WithTitle("My Document");
    Input.Binarize();
    Input.Contrast();
    Input.Deskew();
    Input.DeNoise();
    Input.Dilate();
    Input.EnhanceResolution(300);
    Input.Invert();
    Input.Rotate(90);
    Input.Scale(150); // or Input.Scale(3000, 2000);
    Input.Sharpen();
    Input.ToGrayScale();

    // you don't need all of them
    // most users only need Deskew() and occasionally DeNoise() 

    var Result = Ocr.Read(Input);
    Console.WriteLine(Result.Text);
}

Imports IronOcr

Private Ocr = New IronTesseract()
Using Input = New OcrInput("images\image.png")
	Input.WithTitle("My Document")
	Input.Binarize()
	Input.Contrast()
	Input.Deskew()
	Input.DeNoise()
	Input.Dilate()
	Input.EnhanceResolution(300)
	Input.Invert()
	Input.Rotate(90)
	Input.Scale(150) ' or Input.Scale(3000, 2000);
	Input.Sharpen()
	Input.ToGrayScale()

	' you don't need all of them
	' most users only need Deskew() and occasionally DeNoise() 

	Dim Result = Ocr.Read(Input)
	Console.WriteLine(Result.Text)
End Using

OcrResult Class

using IronOcr;
using System.Drawing; //for image export

// 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 Ocr = new IronTesseract();
Ocr.Configuration.EngineMode = TesseractEngineMode.TesseractAndLstm;
Ocr.Configuration.ReadBarCodes = true;
using (var Input = new OcrInput(@"example.tiff"))
{
    OcrResult Result = Ocr.Read(Input);
    foreach (var Page in Result.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;
        System.Drawing.Bitmap PageImage = Page.ToBitmap(Input);
        int PageWidth = Page.Width;
        int PageHeight = Page.Height;
        foreach (var Paragraph in Page.Paragraphs)
        {
            // Pages -> Paragraphs
            int ParagraphNumber = Paragraph.ParagraphNumber;
            String ParagraphText = Paragraph.Text;
            System.Drawing.Bitmap ParagraphImage = Paragraph.ToBitmap(Input);
            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;
                System.Drawing.Bitmap LineImage = Line.ToBitmap(Input); ;
                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;
                    System.Drawing.Image WordImage = Word.ToBitmap(Input);
                    int WordX_location = Word.X;
                    int WordY_location = Word.Y;
                    int WordWidth = Word.Width;
                    int WordHeight = Word.Height;
                    double WordOcrAccuracy = Word.Confidence;
                    if (Word.Font != null)
                    {
                        // Word.Font is only set when using Tesseract Engine Modes rather than LTSM
                        String FontName = Word.Font.FontName;
                        double FontSize = Word.Font.FontSize;
                        bool IsBold = Word.Font.IsBold;
                        bool IsFixedWidth = Word.Font.IsFixedWidth;
                        bool IsItalic = Word.Font.IsItalic;
                        bool IsSerif = Word.Font.IsSerif;
                        bool IsUnderLined = Word.Font.IsUnderlined;
                        bool IsFancy = Word.Font.IsCaligraphic;
                    }
                    foreach (var Character in Word.Characters)
                    {
                        // Pages -> Paragraphs -> Lines -> Words -> Characters
                        int CharacterNumber = Character.CharacterNumber;
                        String CharacterText = Character.Text;
                        System.Drawing.Bitmap CharacterImage = Character.ToBitmap(Input);
                        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;
                    }
                }
            }
        }
    }
}

Imports IronOcr
Imports System.Drawing 'for image export

' 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/
Private Ocr = New IronTesseract()
Ocr.Configuration.EngineMode = TesseractEngineMode.TesseractAndLstm
Ocr.Configuration.ReadBarCodes = True
Using Input = New OcrInput("example.tiff")
	Dim Result As OcrResult = Ocr.Read(Input)
	For Each Page In Result.Pages
		' Page object
		Dim PageNumber As Integer = Page.PageNumber
		Dim PageText As String = Page.Text
		Dim PageWordCount As Integer = Page.WordCount
		' null if we dont set Ocr.Configuration.ReadBarCodes = true;
		Dim Barcodes() As OcrResult.Barcode = Page.Barcodes
		Dim PageImage As System.Drawing.Bitmap = Page.ToBitmap(Input)
		Dim PageWidth As Integer = Page.Width
		Dim PageHeight As Integer = Page.Height
		For Each Paragraph In Page.Paragraphs
			' Pages -> Paragraphs
			Dim ParagraphNumber As Integer = Paragraph.ParagraphNumber
			Dim ParagraphText As String = Paragraph.Text
			Dim ParagraphImage As System.Drawing.Bitmap = Paragraph.ToBitmap(Input)
			Dim ParagraphX_location As Integer = Paragraph.X
			Dim ParagraphY_location As Integer = Paragraph.Y
			Dim ParagraphWidth As Integer = Paragraph.Width
			Dim ParagraphHeight As Integer = Paragraph.Height
			Dim ParagraphOcrAccuracy As Double = Paragraph.Confidence
			Dim paragrapthText_direction As OcrResult.TextFlow = Paragraph.TextDirection
			For Each Line In Paragraph.Lines
				' Pages -> Paragraphs -> Lines
				Dim LineNumber As Integer = Line.LineNumber
				Dim LineText As String = Line.Text
				Dim LineImage As System.Drawing.Bitmap = Line.ToBitmap(Input)

				Dim LineX_location As Integer = Line.X
				Dim LineY_location As Integer = Line.Y
				Dim LineWidth As Integer = Line.Width
				Dim LineHeight As Integer = Line.Height
				Dim LineOcrAccuracy As Double = Line.Confidence
				Dim LineSkew As Double = Line.BaselineAngle
				Dim LineOffset As Double = Line.BaselineOffset
				For Each Word In Line.Words
					' Pages -> Paragraphs -> Lines -> Words
					Dim WordNumber As Integer = Word.WordNumber
					Dim WordText As String = Word.Text
					Dim WordImage As System.Drawing.Image = Word.ToBitmap(Input)
					Dim WordX_location As Integer = Word.X
					Dim WordY_location As Integer = Word.Y
					Dim WordWidth As Integer = Word.Width
					Dim WordHeight As Integer = Word.Height
					Dim WordOcrAccuracy As Double = Word.Confidence
					If Word.Font IsNot Nothing Then
						' Word.Font is only set when using Tesseract Engine Modes rather than LTSM
						Dim FontName As String = Word.Font.FontName
						Dim FontSize As Double = Word.Font.FontSize
						Dim IsBold As Boolean = Word.Font.IsBold
						Dim IsFixedWidth As Boolean = Word.Font.IsFixedWidth
						Dim IsItalic As Boolean = Word.Font.IsItalic
						Dim IsSerif As Boolean = Word.Font.IsSerif
						Dim IsUnderLined As Boolean = Word.Font.IsUnderlined
						Dim IsFancy As Boolean = Word.Font.IsCaligraphic
					End If
					For Each Character In Word.Characters
						' Pages -> Paragraphs -> Lines -> Words -> Characters
						Dim CharacterNumber As Integer = Character.CharacterNumber
						Dim CharacterText As String = Character.Text
						Dim CharacterImage As System.Drawing.Bitmap = Character.ToBitmap(Input)
						Dim CharacterX_location As Integer = Character.X
						Dim CharacterY_location As Integer = Character.Y
						Dim CharacterWidth As Integer = Character.Width
						Dim CharacterHeight As Integer = Character.Height
						Dim CharacterOcrAccuracy As Double = Character.Confidence
						' Output alternative symbols choices and their probability.
						' Very useful for spellchecking
						Dim Choices() As OcrResult.Choice = Character.Choices
					Next Character
				Next Word
			Next Line
		Next Paragraph
	Next Page
End Using

Create Searchable PDFs by OCR

using IronOcr;

  var Ocr = new IronTesseract();
using (var Input = new OcrInput())
{
    Input.Add(@"images\page1.png")
    Input.Add(@"images\page2.bmp")
    Input.Add(@"images\page3.tiff")

    Input.Deskew();

    var Result = Ocr.Read(Input);
    Result.SaveAsSearchablePdf("searchable.pdf");
}

Imports IronOcr

  Private Ocr = New IronTesseract()
Using Input = New OcrInput()
	Input.Add("images\page1.png") Input.Add("images\page2.bmp") Input.Add("images\page3.tiff") Input.Deskew()

	Dim Result = Ocr.Read(Input)
	Result.SaveAsSearchablePdf("searchable.pdf")
End Using

Tesseract 5 for .NET

using IronOcr;
//..
var Ocr = new IronTesseract();
Ocr.Configuration.TesseractVersion = TesseractVersion.Tesseract5;
// This is default
using (var Input = new OcrInput(@"images\image.png"))
{
    var Result = Ocr.Read(Input);
    Console.WriteLine(Result.Text);
}

Imports IronOcr
'..
Private Ocr = New IronTesseract()
Ocr.Configuration.TesseractVersion = TesseractVersion.Tesseract5
' This is default
Using Input = New OcrInput("images\image.png")
	Dim Result = Ocr.Read(Input)
	Console.WriteLine(Result.Text)
End Using