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); }

Imports IronOcr Imports System Private ocrTesseract = New IronTesseract() Using ocrInput As 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: Dim confidence As Double Dim codeToRun As String = OcrInputFilterWizard.Run("images\image.png", confidence, ocrTesseract) Console.WriteLine(codeToRun) ' Optional: Export modified images so you can view them. For Each page In ocrInput.Pages page.SaveAsImage($"filtered_{page.Index}.bmp") Next page Dim ocrResult = ocrTesseract.Read(ocrInput) Console.WriteLine(ocrResult.Text) 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/ 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; } } } } } }

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 ocrTesseract = New IronTesseract() ocrTesseract.Configuration.ReadBarCodes = True Using ocrInput As New OcrInput("example.tiff") Dim ocrResult As OcrResult = ocrTesseract.Read(ocrInput) For Each page In ocrResult.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 AnyBitmap = page.ToBitmap(ocrInput) Dim PageWidth As Integer = page.Width Dim PageHeight As Integer = page.Height Dim PageRotation As Double = page.Rotation ' angular correction in degrees from OcrInput.Deskew() For Each paragraph In page.Paragraphs ' Pages -> Paragraphs Dim ParagraphNumber As Integer = paragraph.ParagraphNumber Dim ParagraphText As String = paragraph.Text Dim ParagraphImage As AnyBitmap = paragraph.ToBitmap(ocrInput) 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 AnyBitmap = line.ToBitmap(ocrInput) 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 AnyBitmap = word.ToBitmap(ocrInput) 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 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(ocrInput) 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

Compare to Other Components

November 15, 2022

A Comparison between IronOCR and Syncfusion OCR

Syncfusion OCR is a part of a larger PDF document processing package. Syncfusion Essential Studio uses open source Google’s Tesseract Optical Character Recognition engine.

October 13, 2022

A Comparison between IronOCR and AWS OCR

AWS OCR Textract uses machine learning to read and process any type of document.

October 3, 2022

Tesseract Alternatives (2022 Update)

Tesseract uses highly accurate optical character recognition technology that can convert scanned paper documents into searchable digital files.

September 6, 2022

A Comparison between IronOCR and PDFTRON OCR

PDFTron SDK requires a separately downloadable OCR Module as a new optional add-on utility in order to use OCR with the SDK. It is currently available on Windows, Linux, macOS.

September 1, 2022

A Comparison between IronOCR and Tesseract.NET

The Tesseract.net SDK is a product of Patagames, an optical character recognition (OCR) library for .NET projects, and provides a way to add OCR capabilities like text recognition in .NET applications.

June 14, 2022

A Comparison between IronOCR and Dynamsoft OCR

The Dynamsoft.NET OCR library is a .NET component that provides rapid and reliable optical character recognition. It is used for creating .NET desktop applications in C# or VB.NET.

June 9, 2022

A Comparison between IronOCR and Asprise OCR

Asprise C# .NET OCR (optical character recognition) and barcode recognition SDK offers a high-performance API library for you to equip your C# .NET applications.

April 26, 2022

A Comparison between IronOCR and Leadtools OCR

LEADTOOLS is a toolset built to provide you with the most potent image technology available, no matter your programming needs.

April 25, 2022

A Comparison between IronOCR and Abbyy Finereader

Abbyy Finereader allows us to convert Image documents (pictures, scans, PDF files) and screen captures can be converted to editable file formats.