C# OCR Image to Text Tutorial: Convert Images to Text Without Tesseract

using IronOcr;

IronTesseract ocr = new IronTesseract();
using OcrInput input = new OcrInput();
var pageindices = new int[] { 1, 2 };
input.LoadImageFrames(@"img\Potter.LowQuality.tiff", pageindices);
input.Deskew(); // removes rotation and perspective
OcrResult result = ocr.Read(input);
Console.WriteLine(result.Text);

Imports IronOcr

Private ocr As New IronTesseract()
Private OcrInput As using
Private pageindices = New Integer() { 1, 2 }
input.LoadImageFrames("img\Potter.LowQuality.tiff", pageindices)
input.Deskew() ' removes rotation and perspective
Dim result As OcrResult = ocr.Read(input)
Console.WriteLine(result.Text)

using IronOcr;

IronTesseract ocr = new IronTesseract();
using OcrInput input = new OcrInput();
input.Title = "Pdf Title";
var pageindices = new int[] { 1, 2 };
input.LoadImageFrames("example.tiff", pageindices);
OcrResult result = ocr.Read(input);
result.SaveAsSearchablePdf("searchable.pdf");

Imports IronOcr

Private ocr As New IronTesseract()
Private OcrInput As using
input.Title = "Pdf Title"
Dim pageindices = New Integer() { 1, 2 }
input.LoadImageFrames("example.tiff", pageindices)
Dim result As OcrResult = ocr.Read(input)
result.SaveAsSearchablePdf("searchable.pdf")

using IronOcr;

IronTesseract ocr = new IronTesseract();

using OcrInput input = new OcrInput();
input.Title = "Html Title";

// Add more content as required...
input.LoadImage("image2.jpeg");
input.LoadPdf("example.pdf",Password: "password");
var pageindices = new int[] { 1, 2 };
input.LoadImageFrames("example.tiff", pageindices);

OcrResult result = ocr.Read(input);
result.SaveAsHocrFile("hocr.html");

Imports IronOcr

Private ocr As New IronTesseract()

Private OcrInput As using
input.Title = "Html Title"

' Add more content as required...
input.LoadImage("image2.jpeg")
input.LoadPdf("example.pdf",Password:= "password")
Dim pageindices = New Integer() { 1, 2 }
input.LoadImageFrames("example.tiff", pageindices)

Dim result As OcrResult = ocr.Read(input)
result.SaveAsHocrFile("hocr.html")

using IronOcr;

IronTesseract ocr = new IronTesseract();

ocr.Configuration.ReadBarCodes = true;

using OcrInput input = new OcrInput();
input.LoadImage("img/Barcode.png");

OcrResult result = ocr.Read(input);

foreach (var barcode in result.Barcodes)
{
    Console.WriteLine(barcode.Value);
    // type and location properties also exposed
}

Imports IronOcr

Private ocr As New IronTesseract()

ocr.Configuration.ReadBarCodes = True

Using input As New OcrInput()
	input.LoadImage("img/Barcode.png")
	
	Dim result As OcrResult = ocr.Read(input)
	
	For Each barcode In result.Barcodes
		Console.WriteLine(barcode.Value)
		' type and location properties also exposed
	Next barcode
End Using

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

IronTesseract ocr = new IronTesseract();
ocr.Configuration.ReadBarCodes = true;

using OcrInput input = new OcrInput();
var pageindices = new int[] { 1, 2 };
input.LoadImageFrames(@"img\Potter.tiff", pageindices);

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 don't set Ocr.Configuration.ReadBarCodes = true;
    OcrResult.Barcode[] barcodes = page.Barcodes;

    AnyBitmap pageImage = page.ToBitmap(input);
    System.Drawing.Bitmap pageImageLegacy = page.ToBitmap(input);
    double pageWidth = page.Width;
    double 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 paragraphXLocation = paragraph.X;
        int paragraphYLocation = paragraph.Y;
        int paragraphWidth = paragraph.Width;
        int paragraphHeight = paragraph.Height;
        double paragraphOcrAccuracy = paragraph.Confidence;
        var paragraphTextDirection = paragraph.TextDirection;

        foreach (var line in paragraph.Lines)
        {
            // Pages -> Paragraphs -> Lines
            int lineNumber = line.LineNumber;
            String lineText = line.Text;
            AnyBitmap lineImage = line.ToBitmap(input);
            System.Drawing.Bitmap lineImageLegacy = line.ToBitmap(input);
            int lineXLocation = line.X;
            int lineYLocation = 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(input);
                System.Drawing.Image wordImageLegacy = word.ToBitmap(input);
                int wordXLocation = word.X;
                int wordYLocation = 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 fontIsCaligraphic = word.Font.IsCaligraphic;
                }

                foreach (var character in word.Characters)
                {
                    // Pages -> Paragraphs -> Lines -> Words -> Characters
                    int characterNumber = character.CharacterNumber;
                    String characterText = character.Text;
                    AnyBitmap characterImage = character.ToBitmap(input);
                    System.Drawing.Bitmap characterImageLegacy = character.ToBitmap(input);
                    int characterXLocation = character.X;
                    int characterYLocation = character.Y;
                    int characterWidth = character.Width;
                    int characterHeight = character.Height;
                    double characterOcrAccuracy = character.Confidence;

                    // Output alternative symbols choices and their probability.
                    // Very useful for spell checking
                    OcrResult.Choice[] characterChoices = character.Choices;
                }
            }
        }
    }
}

Imports IronOcr
Imports 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

Private ocr As New IronTesseract()
ocr.Configuration.ReadBarCodes = True

Using input As New OcrInput()
	Dim pageindices = New Integer() { 1, 2 }
	input.LoadImageFrames("img\Potter.tiff", pageindices)
	
	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 don't set Ocr.Configuration.ReadBarCodes = true;
		Dim barcodes() As OcrResult.Barcode = page.Barcodes
	
		Dim pageImage As AnyBitmap = page.ToBitmap(input)
		Dim pageImageLegacy As System.Drawing.Bitmap = page.ToBitmap(input)
		Dim pageWidth As Double = page.Width
		Dim pageHeight As Double = 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 paragraphXLocation As Integer = paragraph.X
			Dim paragraphYLocation As Integer = paragraph.Y
			Dim paragraphWidth As Integer = paragraph.Width
			Dim paragraphHeight As Integer = paragraph.Height
			Dim paragraphOcrAccuracy As Double = paragraph.Confidence
			Dim paragraphTextDirection = 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 AnyBitmap = line.ToBitmap(input)
				Dim lineImageLegacy As System.Drawing.Bitmap = line.ToBitmap(input)
				Dim lineXLocation As Integer = line.X
				Dim lineYLocation 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 AnyBitmap = word.ToBitmap(input)
					Dim wordImageLegacy As System.Drawing.Image = word.ToBitmap(input)
					Dim wordXLocation As Integer = word.X
					Dim wordYLocation 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 fontIsCaligraphic 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 AnyBitmap = character.ToBitmap(input)
						Dim characterImageLegacy As System.Drawing.Bitmap = character.ToBitmap(input)
						Dim characterXLocation As Integer = character.X
						Dim characterYLocation 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 spell checking
						Dim characterChoices() As OcrResult.Choice = character.Choices
					Next character
				Next word
			Next line
		Next paragraph
	Next page
End Using

using IronOcr;

var ocr = new IronTesseract();

using (var input = new OcrInput())
{
    // Configure document properties
    input.Title = "Scanned Archive Document";

    // Select pages to process
    var pageIndices = new int[] { 1, 2 };
    input.LoadImageFrames("example.tiff", pageIndices);

    // Create searchable PDF from TIFF
    OcrResult result = ocr.Read(input);
    result.SaveAsSearchablePdf("searchable.pdf");
}

Imports IronOcr

Dim ocr As New IronTesseract()

Using input As New OcrInput()
    ' Configure document properties
    input.Title = "Scanned Archive Document"

    ' Select pages to process
    Dim pageIndices As Integer() = {1, 2}
    input.LoadImageFrames("example.tiff", pageIndices)

    ' Create searchable PDF from TIFF
    Dim result As OcrResult = ocr.Read(input)
    result.SaveAsSearchablePdf("searchable.pdf")
End Using

using IronOcr;

var ocr = new IronTesseract();

using (var input = new OcrInput())
{
    // Set HTML title
    input.Title = "Document Archive";

    // Process multiple document types
    input.LoadImage("image2.jpeg");
    input.LoadPdf("example.pdf", "password");

    // Add TIFF pages
    var pageIndices = new int[] { 1, 2 };
    input.LoadImageFrames("example.tiff", pageIndices);

    // Export as HOCR with position data
    OcrResult result = ocr.Read(input);
    result.SaveAsHocrFile("hocr.html");
}

Imports IronOcr

Dim ocr As New IronTesseract()

Using input As New OcrInput()
    ' Set HTML title
    input.Title = "Document Archive"

    ' Process multiple document types
    input.LoadImage("image2.jpeg")
    input.LoadPdf("example.pdf", "password")

    ' Add TIFF pages
    Dim pageIndices As Integer() = {1, 2}
    input.LoadImageFrames("example.tiff", pageIndices)

    ' Export as HOCR with position data
    Dim result As OcrResult = ocr.Read(input)
    result.SaveAsHocrFile("hocr.html")
End Using

// Enable combined text and barcode recognition
using IronOcr;

var ocr = new IronTesseract();

// Enable barcode detection
ocr.Configuration.ReadBarCodes = true;

using (var input = new OcrInput())
{
    // Load image containing both text and barcodes
    input.LoadImage("img/Barcode.png");

    // Process both text and barcodes
    var result = ocr.Read(input);

    // Extract barcode data
    foreach (var barcode in result.Barcodes)
    {
        Console.WriteLine($"Barcode Value: {barcode.Value}");
        Console.WriteLine($"Format: {barcode.Format}");
    }
}

Imports IronOcr

Dim ocr As New IronTesseract()

' Enable barcode detection
ocr.Configuration.ReadBarCodes = True

Using input As New OcrInput()
    ' Load image containing both text and barcodes
    input.LoadImage("img/Barcode.png")

    ' Process both text and barcodes
    Dim result = ocr.Read(input)

    ' Extract barcode data
    For Each barcode In result.Barcodes
        Console.WriteLine($"Barcode Value: {barcode.Value}")
        Console.WriteLine($"Format: {barcode.Format}")
    Next
End Using

using System;
using IronOcr;
using IronSoftware.Drawing;

// Configure with barcode support
IronTesseract ocr = new IronTesseract
{
    Configuration = { ReadBarCodes = true }
};

using OcrInput input = new OcrInput();

// Process multi-page document
int[] pageIndices = { 1, 2 };
input.LoadImageFrames(@"img\Potter.tiff", pageIndices);

OcrResult result = ocr.Read(input);

// Navigate the complete results hierarchy
foreach (var page in result.Pages)
{
    // Page-level data
    int pageNumber = page.PageNumber;
    string pageText = page.Text;
    int pageWordCount = page.WordCount;

    // Extract page elements
    OcrResult.Barcode[] barcodes = page.Barcodes;
    AnyBitmap pageImage = page.ToBitmap();
    double pageWidth = page.Width;
    double pageHeight = page.Height;

    foreach (var paragraph in page.Paragraphs)
    {
        // Paragraph properties
        int paragraphNumber = paragraph.ParagraphNumber;
        string paragraphText = paragraph.Text;
        double paragraphConfidence = paragraph.Confidence;
        var textDirection = paragraph.TextDirection;

        foreach (var line in paragraph.Lines)
        {
            // Line details including baseline information
            string lineText = line.Text;
            double lineConfidence = line.Confidence;
            double baselineAngle = line.BaselineAngle;
            double baselineOffset = line.BaselineOffset;

            foreach (var word in line.Words)
            {
                // Word-level data
                string wordText = word.Text;
                double wordConfidence = word.Confidence;

                // Font information (when available)
                if (word.Font != null)
                {
                    string fontName = word.Font.FontName;
                    double fontSize = word.Font.FontSize;
                    bool isBold = word.Font.IsBold;
                    bool isItalic = word.Font.IsItalic;
                }

                foreach (var character in word.Characters)
                {
                    // Character-level analysis
                    string charText = character.Text;
                    double charConfidence = character.Confidence;

                    // Alternative character choices for spell-checking
                    OcrResult.Choice[] alternatives = character.Choices;
                }
            }
        }
    }
}

Imports System
Imports IronOcr
Imports IronSoftware.Drawing

' Configure with barcode support
Dim ocr As New IronTesseract With {
    .Configuration = New TesseractConfiguration With {
        .ReadBarCodes = True
    }
}

Using input As New OcrInput()

    ' Process multi-page document
    Dim pageIndices As Integer() = {1, 2}
    input.LoadImageFrames("img\Potter.tiff", pageIndices)

    Dim result As OcrResult = ocr.Read(input)

    ' Navigate the complete results hierarchy
    For Each page In result.Pages
        ' Page-level data
        Dim pageNumber As Integer = page.PageNumber
        Dim pageText As String = page.Text
        Dim pageWordCount As Integer = page.WordCount

        ' Extract page elements
        Dim barcodes As OcrResult.Barcode() = page.Barcodes
        Dim pageImage As AnyBitmap = page.ToBitmap()
        Dim pageWidth As Double = page.Width
        Dim pageHeight As Double = page.Height

        For Each paragraph In page.Paragraphs
            ' Paragraph properties
            Dim paragraphNumber As Integer = paragraph.ParagraphNumber
            Dim paragraphText As String = paragraph.Text
            Dim paragraphConfidence As Double = paragraph.Confidence
            Dim textDirection = paragraph.TextDirection

            For Each line In paragraph.Lines
                ' Line details including baseline information
                Dim lineText As String = line.Text
                Dim lineConfidence As Double = line.Confidence
                Dim baselineAngle As Double = line.BaselineAngle
                Dim baselineOffset As Double = line.BaselineOffset

                For Each word In line.Words
                    ' Word-level data
                    Dim wordText As String = word.Text
                    Dim wordConfidence As Double = word.Confidence

                    ' Font information (when available)
                    If word.Font IsNot Nothing Then
                        Dim fontName As String = word.Font.FontName
                        Dim fontSize As Double = word.Font.FontSize
                        Dim isBold As Boolean = word.Font.IsBold
                        Dim isItalic As Boolean = word.Font.IsItalic
                    End If

                    For Each character In word.Characters
                        ' Character-level analysis
                        Dim charText As String = character.Text
                        Dim charConfidence As Double = character.Confidence

                        ' Alternative character choices for spell-checking
                        Dim alternatives As OcrResult.Choice() = character.Choices
                    Next
                Next
            Next
        Next
    Next
End Using