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.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; Bitmap PageImage = page.ToBitmap(Input); 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; 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; 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; 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; foreach (var character in word.Characters) { // Pages -> Paragraphs -> Lines -> Words -> Characters int CharacterNumber = character.CharacterNumber; string CharacterText = character.Text; 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.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 Bitmap = page.ToBitmap(Input) 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 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 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 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 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 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

IronOCR Blog

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 17, 2022

Online OCR converter — Free Online Tools

This section is about free online OCR tools. Online OCR tools exist to help us with the process of converting paper-based documents into digital texts.

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 10, 2022

OCR in Windows 11 (Free Online Tools)

Photo Scan is a free OCR software available for Windows 11. It is available on the Microsoft store for free.

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.

April 8, 2022

Tesseract Ocr in Windows (Code Example Tutorial)

In this tutorial we will take you through the steps in order to install Tesseract on Windows 10 machine.