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

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)

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)

' PM> Install IronOcr.Languages.Arabic
Imports IronOcr

Private ocr As New IronTesseract()
ocr.Language = OcrLanguage.Arabic

Using input As New OcrInput()
	input.LoadImageFrame("img/arabic.gif", 1)
	' add image filters if needed
	' In this case, even thought input is very low quality
	' IronTesseract can read what conventional Tesseract cannot.
	
	Dim result As OcrResult = ocr.Read(input)
	
	' Console can't print Arabic on Windows easily.
	' Let's save to disk instead.
	result.SaveAsTextFile("arabic.txt")
End Using

' PM> Install IronOcr.Languages.Arabic
Imports IronOcr

Private ocr As New IronTesseract()
ocr.Language = OcrLanguage.Arabic

Using input As New OcrInput()
	input.LoadImageFrame("img/arabic.gif", 1)
	' add image filters if needed
	' In this case, even thought input is very low quality
	' IronTesseract can read what conventional Tesseract cannot.
	
	Dim result As OcrResult = ocr.Read(input)
	
	' Console can't print Arabic on Windows easily.
	' Let's save to disk instead.
	result.SaveAsTextFile("arabic.txt")
End Using

Imports IronOcr

Private ocr As New IronTesseract()
ocr.Language = OcrLanguage.ChineseSimplified

' We can add any number of languages.
ocr.AddSecondaryLanguage(OcrLanguage.English)
' Optionally add custom tesseract .traineddata files by specifying a file path

Using input As New OcrInput()
	input.LoadImage("img/MultiLanguage.jpeg")
	Dim result As OcrResult = ocr.Read(input)
	result.SaveAsTextFile("MultiLanguage.txt")
End Using

Imports IronOcr

Private ocr As New IronTesseract()
ocr.Language = OcrLanguage.ChineseSimplified

' We can add any number of languages.
ocr.AddSecondaryLanguage(OcrLanguage.English)
' Optionally add custom tesseract .traineddata files by specifying a file path

Using input As New OcrInput()
	input.LoadImage("img/MultiLanguage.jpeg")
	Dim result As OcrResult = ocr.Read(input)
	result.SaveAsTextFile("MultiLanguage.txt")
End Using

Imports IronOcr

Private ocr As New IronTesseract()

Private OcrInput As using
input.LoadImage("image1.jpeg")
input.LoadImage("image2.png")
Dim pageindices = New Integer() { 1, 2 }
input.LoadImageFrames("image3.gif", pageindices)

Dim result As OcrResult = ocr.Read(input)

Console.WriteLine($"{result.Pages.Length} Pages") ' 3 Pages

Imports IronOcr

Private ocr As New IronTesseract()

Private OcrInput As using
input.LoadImage("image1.jpeg")
input.LoadImage("image2.png")
Dim pageindices = New Integer() { 1, 2 }
input.LoadImageFrames("image3.gif", pageindices)

Dim result As OcrResult = ocr.Read(input)

Console.WriteLine($"{result.Pages.Length} Pages") ' 3 Pages

Imports IronOcr

Private ocr As New IronTesseract()
Private OcrInput As using
input.LoadPdf("example.pdf", Password:= "password")
' We can also select specific PDF page numbers to OCR

Dim result As OcrResult = ocr.Read(input)

Console.WriteLine(result.Text)
Console.WriteLine($"{result.Pages.Length} Pages")
' 1 page for every page of the PDF

Imports IronOcr

Private ocr As New IronTesseract()
Private OcrInput As using
input.LoadPdf("example.pdf", Password:= "password")
' We can also select specific PDF page numbers to OCR

Dim result As OcrResult = ocr.Read(input)

Console.WriteLine(result.Text)
Console.WriteLine($"{result.Pages.Length} Pages")
' 1 page for every page of the PDF

Imports IronOcr

Private ocr As New IronTesseract()

Private OcrInput As using
input.Title = "Pdf Metadata Name"
input.LoadPdf("example.pdf", Password:= "password")
Dim result As OcrResult = ocr.Read(input)
result.SaveAsSearchablePdf("searchable.pdf")

Imports IronOcr

Private ocr As New IronTesseract()

Private OcrInput As using
input.Title = "Pdf Metadata Name"
input.LoadPdf("example.pdf", Password:= "password")
Dim result As OcrResult = 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")

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")

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")

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")

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

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

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

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

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

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

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

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

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

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