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

Supported Platforms

Designed for C#, F#, & VB.NET running on .NET 5, Core, Standard, or Framework

Human Support Directly From Our Development Team

Whether it's product, integration or licensing queries, the Iron product development team is on hand to support all of your questions. Get in touch and start a dialog with Iron to make the most of our library in your project.

Ask a Question

Image to Text OCR
for Visual Studio

Pass IronOCR single or multi page scanned images to receive all text, barcode, & QR content in return. The OCR library provides a set of classes to add OCR functionality into Web, Desktop or Console .Net Applications. Input formats can include PDF, JPG, PNG, GIF, BMP and TIFF.

Designed for C#, VB.Net, .Net

Read the How-To Tutorials

High Accuracy
at High Speeds

The OCR (Optical Character Recognition) engine views pages formatted with multiple popular fonts, weights, italics, and underlines for accurate text reading. Cropping classes further assists OCR to perform at speed and with pinpoint accuracy. Iron’s multithreaded engine accelerates OCR speeds for multi-page documents on multi-core servers.

Get Started

Advanced Image Pre-processing for Consistent Results Every time

What really makes IronOCR special is its ability to read badly scanned documents. Its unique pre-processing library reduces background noise, rotation, distortion and skewed alignment as well as simplifying colours and enhancing resolution & contrast. Iron’s AutoOCR and Advanced OCR settings provide developers with the tools to achieve the best possible results, every time.

Learn More

Support for Languages from across the globe

Language packs available for: Arabic, Simplified Chinese, Traditional Chinese, Danish, English, Finnish, French, German, Hebrew, Italian, Japanese, Korean, Portuguese, Russian, Spanish, and Swedish. Other languages can be supported by request.

View Language Packs

Output content into your project as Structured Data

IronOCR outputs content as plain text and barcode data. An alternative structured data object model allows developers to receive all content in the format of structured Headings, Paragraphs, Lines, Words and Characters for input directly into .Net applications.

See the Object Reference