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; } } } } } }

Compare to Other Components

May 17, 2023

A Comparison Between Google OCR & IronOCR

Google Cloud Vision API is a Google Cloud OCR client library which supports C# language. It allows C# developers to easily integrate Computer Vision detection features in software applications.

May 17, 2023

A Comparison Between OCR Software By Iris & IronOCR

Iris OCR SDK is a modular software toolkit that enables your applications to convert image text into editable files and provide other text recognition services.

May 9, 2023

A Comparison Between IronOCR and Nanonets OCR

Nanonets OCR API is a REST API that provides real-time data extraction tailored to your business needs for automated workflows.

January 27, 2023

A Comparison between IronOCR and Aspose.OCR

Aspose.OCR for .NET is a robust optical character recognition API. Developers can easily add OCR functionalities to their applications.

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

Comparison between IronOCR and AWS Textract 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.