Read Text from Images with C# OCR

// This code snippet uses the IronOcr library to perform Optical Character Recognition (OCR)
// on an image file and print the extracted text to the console.

// To use IronOcr, ensure you have installed the package via NuGet Package Manager:
// PM> Install-Package IronOcr

using IronOcr;

try
{
    // Create an instance of IronTesseract, which is used to perform OCR on images.
    var ocrEngine = new IronTesseract();

    // Specify the file path to the image you want to process. 
    // Ensure the path is correct; it's currently set to a relative path.
    var filePath = @"img\Screenshot.png";

    // Use the Read method to perform OCR on the specified image file.
    // This returns an OcrResult which contains the recognized text.
    using (var input = new OcrInput(filePath))
    {
        OcrResult result = ocrEngine.Read(input);

        // Output the extracted text to the console.
        Console.WriteLine(result.Text);
    }
}
catch (OcrException ex)
{
    // Handle any OCR-specific exceptions that might occur
    Console.WriteLine("An error occurred while processing the image: " + ex.Message);
}
catch (Exception ex)
{
    // Handle any general exceptions that might occur
    Console.WriteLine("An error occurred: " + ex.Message);
}

' This code snippet uses the IronOcr library to perform Optical Character Recognition (OCR)

' on an image file and print the extracted text to the console.



' To use IronOcr, ensure you have installed the package via NuGet Package Manager:

' PM> Install-Package IronOcr



Imports IronOcr



Try

	' Create an instance of IronTesseract, which is used to perform OCR on images.

	Dim ocrEngine = New IronTesseract()



	' Specify the file path to the image you want to process. 

	' Ensure the path is correct; it's currently set to a relative path.

	Dim filePath = "img\Screenshot.png"



	' Use the Read method to perform OCR on the specified image file.

	' This returns an OcrResult which contains the recognized text.

	Using input = New OcrInput(filePath)

		Dim result As OcrResult = ocrEngine.Read(input)



		' Output the extracted text to the console.

		Console.WriteLine(result.Text)

	End Using

Catch ex As OcrException

	' Handle any OCR-specific exceptions that might occur

	Console.WriteLine("An error occurred while processing the image: " & ex.Message)

Catch ex As Exception

	' Handle any general exceptions that might occur

	Console.WriteLine("An error occurred: " & ex.Message)

End Try

using IronOcr;

// Create an instance of the IronTesseract OCR engine.
IronTesseract ocr = new IronTesseract();

// Using statement to ensure resources are disposed of correctly.
using (OcrInput input = new OcrInput())
{
    // Specify the pages to be read from a multi-page TIFF file.
    int[] pageIndices = new int[] { 1, 2 };

    // Load specified image frames (pages) from the TIFF file into the input object.
    // Ensure the file path is correct, adjust as needed if the directory structure is different.
    input.LoadImageFrames(@"img\Potter.tiff", pageIndices);

    // Perform OCR on the loaded image frames.
    // The Read method analyses the image frames and extracts text.
    OcrResult result = ocr.Read(input);

    // Output the extracted text to the console.
    // If reading pages fails, result.Text will be empty or contain error messages.
    Console.WriteLine(result.Text);
}

Imports IronOcr



' Create an instance of the IronTesseract OCR engine.

Private ocr As New IronTesseract()



' Using statement to ensure resources are disposed of correctly.

Using input As New OcrInput()

	' Specify the pages to be read from a multi-page TIFF file.

	Dim pageIndices() As Integer = { 1, 2 }



	' Load specified image frames (pages) from the TIFF file into the input object.

	' Ensure the file path is correct, adjust as needed if the directory structure is different.

	input.LoadImageFrames("img\Potter.tiff", pageIndices)



	' Perform OCR on the loaded image frames.

	' The Read method analyses the image frames and extracts text.

	Dim result As OcrResult = ocr.Read(input)



	' Output the extracted text to the console.

	' If reading pages fails, result.Text will be empty or contain error messages.

	Console.WriteLine(result.Text)

End Using

// Include the necessary namespace for IronOcr
using IronOcr;
using System;

// Create a new instance of the IronTesseract class, which is responsible for OCR operations
var ocr = new IronTesseract();

try
{
    // Create a new OCR input object that represents the images to be processed
    using (var input = new OcrInput())
    {
        // Specify the indices of the pages in a multi-page image file you want to process
        // Typically, indices are 0-based, but check if the library needs 1-based indices
        var pageIndices = new int[] { 0, 1 }; // Adjust indices according to your requirements

        // Load specific frames/pages from a TIFF file into the OCR input object
        input.LoadImageFrames(@"img\Potter.LowQuality.tiff", pageIndices);

        // Apply a deskew transformation to the input to correct any rotation or perspective distortion
        input.Deskew(); // This method helps in removing rotation and perspective to improve OCR accuracy

        // Perform OCR on the processed input and obtain the result
        OcrResult result = ocr.Read(input);

        // Output the recognized text to the console
        Console.WriteLine("Recognized Text:");
        Console.WriteLine(result.Text);
    }
}
catch (Exception ex)
{
    // Handle potential exceptions such as file not found, incorrect image format, etc.
    Console.WriteLine("An error occurred during OCR processing: " + ex.Message);
}

' Include the necessary namespace for IronOcr

Imports IronOcr

Imports System



' Create a new instance of the IronTesseract class, which is responsible for OCR operations

Private ocr = New IronTesseract()



Try

	' Create a new OCR input object that represents the images to be processed

	Using input = New OcrInput()

		' Specify the indices of the pages in a multi-page image file you want to process

		' Typically, indices are 0-based, but check if the library needs 1-based indices

		Dim pageIndices = New Integer() { 0, 1 } ' Adjust indices according to your requirements



		' Load specific frames/pages from a TIFF file into the OCR input object

		input.LoadImageFrames("img\Potter.LowQuality.tiff", pageIndices)



		' Apply a deskew transformation to the input to correct any rotation or perspective distortion

		input.Deskew() ' This method helps in removing rotation and perspective to improve OCR accuracy



		' Perform OCR on the processed input and obtain the result

		Dim result As OcrResult = ocr.Read(input)



		' Output the recognized text to the console

		Console.WriteLine("Recognized Text:")

		Console.WriteLine(result.Text)

	End Using

Catch ex As Exception

	' Handle potential exceptions such as file not found, incorrect image format, etc.

	Console.WriteLine("An error occurred during OCR processing: " & ex.Message)

End Try

using IronOcr; 

// Initialize a new instance of the IronTesseract class which handles OCR operations
IronTesseract ocr = new IronTesseract();

// Configure for optimal speed by excluding specific characters from OCR consideration
ocr.Configuration.BlackListCharacters = "~`$#^*_{[]}
\\";
// Set the page segmentation mode to automatic
ocr.Configuration.PageSegmentationMode = TesseractPageSegmentationMode.Auto;
// Use the fast version of the English OCR language
ocr.Language = OcrLanguage.EnglishFast;

// Create an instance of OcrInput which will be used to load the document to be processed
using (OcrInput input = new OcrInput())
{
    // Specify the image frames to load from a multi-page image file
    int[] pageIndices = new int[] { 1, 2 };
    
    // Load specified pages from the image file into the OcrInput instance
    input.LoadImageFrames(@"img\Potter.tiff", pageIndices);

    // Read the text from the input images and store the OCR result
    OcrResult result = ocr.Read(input);
    
    // Output the textual result of the OCR process to the console
    Console.WriteLine(result.Text);
}

Imports IronOcr



' Initialize a new instance of the IronTesseract class which handles OCR operations

Private ocr As New IronTesseract()



' Configure for optimal speed by excluding specific characters from OCR consideration

ocr.Configuration.BlackListCharacters = "~`$#^*_{[]}
\"

' Set the page segmentation mode to automatic

ocr.Configuration.PageSegmentationMode = TesseractPageSegmentationMode.Auto

' Use the fast version of the English OCR language

ocr.Language = OcrLanguage.EnglishFast



' Create an instance of OcrInput which will be used to load the document to be processed

Using input As New OcrInput()

	' Specify the image frames to load from a multi-page image file

	Dim pageIndices() As Integer = { 1, 2 }



	' Load specified pages from the image file into the OcrInput instance

	input.LoadImageFrames("img\Potter.tiff", pageIndices)



	' Read the text from the input images and store the OCR result

	Dim result As OcrResult = ocr.Read(input)



	' Output the textual result of the OCR process to the console

	Console.WriteLine(result.Text)

End Using

using IronOcr; // Namespace for IronOcr library
using IronSoftware.Drawing; // Namespace reference for drawing-related classes

// Create an instance of the IronTesseract class for OCR processing
var ocr = new IronTesseract();

// Using statement ensures that resources are automatically released after use
using (var input = new OcrInput())
{
    // Define a rectangle area to focus OCR processing on a specific portion of the image.
    // This can significantly speed up the process by limiting the area to be analyzed.
    // Rectangle arguments: x = 215, y = 1250, width = 1335, height = 280
    var contentArea = new System.Drawing.Rectangle(x: 215, y: 1250, width: 1335, height: 280);

    // Load the image with a specific area of interest
    input.AddImage("img/ComSci.png", contentArea);

    // Perform OCR on the loaded image input
    OcrResult result = ocr.Read(input);

    // Output the recognized text to the console
    Console.WriteLine(result.Text);
}

Imports IronOcr ' Namespace for IronOcr library

Imports IronSoftware.Drawing ' Namespace reference for drawing-related classes



' Create an instance of the IronTesseract class for OCR processing

Private ocr = New IronTesseract()



' Using statement ensures that resources are automatically released after use

Using input = New OcrInput()

	' Define a rectangle area to focus OCR processing on a specific portion of the image.

	' This can significantly speed up the process by limiting the area to be analyzed.

	' Rectangle arguments: x = 215, y = 1250, width = 1335, height = 280

	Dim contentArea = New System.Drawing.Rectangle(x:= 215, y:= 1250, width:= 1335, height:= 280)



	' Load the image with a specific area of interest

	input.AddImage("img/ComSci.png", contentArea)



	' Perform OCR on the loaded image input

	Dim result As OcrResult = ocr.Read(input)



	' Output the recognized text to the console

	Console.WriteLine(result.Text)

End Using

// PM> Install IronOcr.Languages.Arabic
using IronOcr;

// Create an instance of the IronTesseract class for OCR operations.
var ocr = new IronTesseract();

// Set the OCR language to Arabic.
ocr.Language = OcrLanguage.Arabic;

// Use a 'using' block for OcrInput to ensure proper disposal of resources.
using (var input = new OcrInput())
{
    // Load the first frame of the image located at "img/arabic.gif".
    input.AddImage("img/arabic.gif");
    
    // Optional: Add image filters if necessary for better OCR performance.
    // In this case, even though the input is very low quality,
    // IronTesseract can read what conventional Tesseract cannot.

    // Perform OCR to get the result.
    var result = ocr.Read(input);

    // Save the OCR result to a text file because the console might not display Arabic correctly on Windows.
    result.SaveAsTextFile("arabic.txt");
}

' PM> Install IronOcr.Languages.Arabic

Imports IronOcr



' Create an instance of the IronTesseract class for OCR operations.

Private ocr = New IronTesseract()



' Set the OCR language to Arabic.

ocr.Language = OcrLanguage.Arabic



' Use a 'using' block for OcrInput to ensure proper disposal of resources.

Using input = New OcrInput()

	' Load the first frame of the image located at "img/arabic.gif".

	input.AddImage("img/arabic.gif")



	' Optional: Add image filters if necessary for better OCR performance.

	' In this case, even though the input is very low quality,

	' IronTesseract can read what conventional Tesseract cannot.



	' Perform OCR to get the result.

	Dim result = ocr.Read(input)



	' Save the OCR result to a text file because the console might not display Arabic correctly on Windows.

	result.SaveAsTextFile("arabic.txt")

End Using

// Include the necessary namespace for IronOcr functionality
using IronOcr;

// Create an instance of IronTesseract, which is used for OCR operations
var ocr = new IronTesseract();

// Set the primary language for OCR processing to Chinese Simplified
ocr.Language = OcrLanguage.ChineseSimplified;

// We can add any number of secondary languages for OCR processing.
// Here, English is added as a secondary language.
ocr.AddSecondaryLanguage(OcrLanguage.English);

// Optionally, custom Tesseract '.traineddata' files can be added by specifying a file path.
// This is useful for languages that are not supported out of the box or for improving existing language support.

// Using a using statement to ensure proper disposal of resources after OCR operation
using (var input = new OcrInput())
{
    // Load the image that contains multi-language text for OCR processing
    input.AddImage("img/MultiLanguage.jpeg");

    // Perform OCR on the input and retrieve the result
    var result = ocr.Read(input);

    // Save the recognized text as a text file with the specified filename
    result.SaveAsTextFile("MultiLanguage.txt");
}

// Note: Ensure that the necessary IronOcr package is installed and referenced in your project.
// Also, make sure that the image path is correct and accessible by the application.

' Include the necessary namespace for IronOcr functionality

Imports IronOcr



' Create an instance of IronTesseract, which is used for OCR operations

Private ocr = New IronTesseract()



' Set the primary language for OCR processing to Chinese Simplified

ocr.Language = OcrLanguage.ChineseSimplified



' We can add any number of secondary languages for OCR processing.

' Here, English is added as a secondary language.

ocr.AddSecondaryLanguage(OcrLanguage.English)



' Optionally, custom Tesseract '.traineddata' files can be added by specifying a file path.

' This is useful for languages that are not supported out of the box or for improving existing language support.



' Using a using statement to ensure proper disposal of resources after OCR operation

Using input = New OcrInput()

	' Load the image that contains multi-language text for OCR processing

	input.AddImage("img/MultiLanguage.jpeg")



	' Perform OCR on the input and retrieve the result

	Dim result = ocr.Read(input)



	' Save the recognized text as a text file with the specified filename

	result.SaveAsTextFile("MultiLanguage.txt")

End Using



' Note: Ensure that the necessary IronOcr package is installed and referenced in your project.

' Also, make sure that the image path is correct and accessible by the application.

// Required namespace for OCR operations
using IronOcr;

// Create a new instance of IronTesseract to perform OCR operations
IronTesseract ocr = new IronTesseract();

// Using statement to ensure proper disposal of OcrInput resources
using (OcrInput input = new OcrInput())
{
    // Load various images into the input object for OCR processing
    input.AddImage("image1.jpeg");
    input.AddImage("image2.png");

    // Specify which frames to load from a multi-frame image (e.g., GIF)
    int[] pageIndices = { 1, 2 };
    input.AddImageFrames("image3.gif", pageIndices);

    // Perform OCR on the loaded images and retrieve the result
    OcrResult result = ocr.Read(input);

    // Output the number of pages processed to the console
    Console.WriteLine($"{result.Pages.Count} Pages processed."); // Expected: 3 Pages
}

' Required namespace for OCR operations

Imports IronOcr



' Create a new instance of IronTesseract to perform OCR operations

Private ocr As New IronTesseract()



' Using statement to ensure proper disposal of OcrInput resources

Using input As New OcrInput()

	' Load various images into the input object for OCR processing

	input.AddImage("image1.jpeg")

	input.AddImage("image2.png")



	' Specify which frames to load from a multi-frame image (e.g., GIF)

	Dim pageIndices() As Integer = { 1, 2 }

	input.AddImageFrames("image3.gif", pageIndices)



	' Perform OCR on the loaded images and retrieve the result

	Dim result As OcrResult = ocr.Read(input)



	' Output the number of pages processed to the console

	Console.WriteLine($"{result.Pages.Count} Pages processed.") ' Expected: 3 Pages

End Using

using IronOcr;

// Instantiate the IronTesseract object, which will handle OCR processing.
IronTesseract ocr = new IronTesseract();

// Create an OcrInput object to hold the images to be processed.
// The 'using' statement ensures that resources are freed when the operation is complete.
using (OcrInput input = new OcrInput())
{
    // Define the indices of the pages to load from a multi-frame TIFF image.
    // This example loads the first and second pages.
    int[] pageIndices = new int[] { 0, 1 }; // Corrected indices to start from 0

    // Load the specified image frames (pages) from the TIFF file.
    // The LoadImageFrames function reads specific frames of a TIFF file as indicated by the indices.
    input.LoadImageFrames("MultiFrame.Tiff", pageIndices);

    // Perform OCR on the input and store the result.
    OcrResult result = ocr.Read(input);

    // Output the recognized text to the console.
    Console.WriteLine(result.Text);

    // Output the number of pages processed, noting that each frame corresponds to a page.
    Console.WriteLine($"{result.Pages.Count} Pages");
    // Note: One page is returned for each frame (page) in the TIFF input.
}

Imports IronOcr



' Instantiate the IronTesseract object, which will handle OCR processing.

Private ocr As New IronTesseract()



' Create an OcrInput object to hold the images to be processed.

' The 'using' statement ensures that resources are freed when the operation is complete.

Using input As New OcrInput()

	' Define the indices of the pages to load from a multi-frame TIFF image.

	' This example loads the first and second pages.

	Dim pageIndices() As Integer = { 0, 1 } ' Corrected indices to start from 0



	' Load the specified image frames (pages) from the TIFF file.

	' The LoadImageFrames function reads specific frames of a TIFF file as indicated by the indices.

	input.LoadImageFrames("MultiFrame.Tiff", pageIndices)



	' Perform OCR on the input and store the result.

	Dim result As OcrResult = ocr.Read(input)



	' Output the recognized text to the console.

	Console.WriteLine(result.Text)



	' Output the number of pages processed, noting that each frame corresponds to a page.

	Console.WriteLine($"{result.Pages.Count} Pages")

	' Note: One page is returned for each frame (page) in the TIFF input.

End Using

using System; // Import system namespace for Console usage
using IronOcr; // Import IronOcr namespace to use OCR functionalities

// Create a new instance of IronTesseract, which is the main class for OCR operations
IronTesseract ocr = new IronTesseract();

// Create an OcrInput object within a using statement to ensure it is disposed of correctly after use
using (OcrInput input = new OcrInput())
{
    try
    {
        // Load the PDF file into the OcrInput object, providing a password if the PDF is password-protected.
        // If the PDF does not have a password, consider providing null or an empty string for the password parameter.
        input.LoadPdf("example.pdf", "password");

        // Perform OCR on the loaded input and store the result
        OcrResult result = ocr.Read(input);

        // Output the recognized text to the console
        Console.WriteLine(result.Text);

        // Output the number of pages recognized in the PDF
        Console.WriteLine($"{result.Pages.Count} Pages");
        // Note: Use result.Pages.Count instead of result.Pages.Length for better C# practices with collections
    }
    catch (Exception ex)
    {
        // In case of exceptions, output the error message to the console
        Console.WriteLine("An error occurred during OCR processing: " + ex.Message);
    }
}

Imports System ' Import system namespace for Console usage

Imports IronOcr ' Import IronOcr namespace to use OCR functionalities



' Create a new instance of IronTesseract, which is the main class for OCR operations

Private ocr As New IronTesseract()



' Create an OcrInput object within a using statement to ensure it is disposed of correctly after use

Using input As New OcrInput()

	Try

		' Load the PDF file into the OcrInput object, providing a password if the PDF is password-protected.

		' If the PDF does not have a password, consider providing null or an empty string for the password parameter.

		input.LoadPdf("example.pdf", "password")



		' Perform OCR on the loaded input and store the result

		Dim result As OcrResult = ocr.Read(input)



		' Output the recognized text to the console

		Console.WriteLine(result.Text)



		' Output the number of pages recognized in the PDF

		Console.WriteLine($"{result.Pages.Count} Pages")

		' Note: Use result.Pages.Count instead of result.Pages.Length for better C# practices with collections

	Catch ex As Exception

		' In case of exceptions, output the error message to the console

		Console.WriteLine("An error occurred during OCR processing: " & ex.Message)

	End Try

End Using

using IronOcr;

// Initializes a new instance of the IronTesseract class
IronTesseract ocr = new IronTesseract();

// Using block to ensure that resources are disposed of properly
using (OcrInput input = new OcrInput())
{
    // Sets the title for the OCR input
    input.Title = "Quarterly Report";

    // Loads individual images into the OCR input
    input.AddImage("image1.jpeg");
    input.AddImage("image2.png");

    // Define specific page indices to load from an image with multiple frames
    int[] pageIndices = new int[] { 1, 2 };

    // Loads specific frames from a multi-frame image (e.g., GIF)
    input.AddImageFrames("image3.gif", pageIndices);

    // Performs OCR on the loaded images and stores the result
    OcrResult result = ocr.Read(input);

    // Saves the OCR result as a searchable PDF
    result.SaveAsSearchablePdf("searchable.pdf");
}

Imports IronOcr



' Initializes a new instance of the IronTesseract class

Private ocr As New IronTesseract()



' Using block to ensure that resources are disposed of properly

Using input As New OcrInput()

	' Sets the title for the OCR input

	input.Title = "Quarterly Report"



	' Loads individual images into the OCR input

	input.AddImage("image1.jpeg")

	input.AddImage("image2.png")



	' Define specific page indices to load from an image with multiple frames

	Dim pageIndices() As Integer = { 1, 2 }



	' Loads specific frames from a multi-frame image (e.g., GIF)

	input.AddImageFrames("image3.gif", pageIndices)



	' Performs OCR on the loaded images and stores the result

	Dim result As OcrResult = ocr.Read(input)



	' Saves the OCR result as a searchable PDF

	result.SaveAsSearchablePdf("searchable.pdf")

End Using

using IronOcr;

// Create an instance of the IronTesseract engine
var ocr = new IronTesseract();

// Use a using statement to ensure input resources are disposed of properly
using (var input = new OcrInput())
{
    // Set a title for the input which might be useful for metadata information
    input.Title = "Pdf Metadata Name";

    // Load the PDF file into the OCR input. If the PDF is password protected, provide the password
    input.LoadPdf("example.pdf", "password");

    // Process the OCR operation on the loaded input
    var result = ocr.Read(input);

    // Save the result as a searchable PDF
    result.SaveAsSearchablePdf("searchable.pdf");
}

Imports IronOcr



' Create an instance of the IronTesseract engine

Private ocr = New IronTesseract()



' Use a using statement to ensure input resources are disposed of properly

Using input = New OcrInput()

	' Set a title for the input which might be useful for metadata information

	input.Title = "Pdf Metadata Name"



	' Load the PDF file into the OCR input. If the PDF is password protected, provide the password

	input.LoadPdf("example.pdf", "password")



	' Process the OCR operation on the loaded input

	Dim result = ocr.Read(input)



	' Save the result as a searchable PDF

	result.SaveAsSearchablePdf("searchable.pdf")

End Using

// Import necessary namespace for OCR functionality using IronOCR library
using IronOcr;

// Instantiate IronTesseract object for OCR operations
var ocr = new IronTesseract();

// Utilize using statement for automatic disposal of OcrInput object after usage
using (var input = new OcrInput())
{
    // Set a title for the OCR input, useful for identifying the content in larger projects
    input.Title = "Pdf Title";

    // Define the page indices of the images that are to be processed
    var pageIndices = new int[] { 1, 2 };

    // Load images from the specified TIFF file, using the defined page indices
    input.LoadImageFrames("example.tiff", pageIndices);

    // Perform OCR on the input and store the result
    OcrResult result = ocr.Read(input);

    // Save the OCR result as a searchable PDF document
    result.SaveAsSearchablePdf("searchable.pdf");
}

' Import necessary namespace for OCR functionality using IronOCR library

Imports IronOcr



' Instantiate IronTesseract object for OCR operations

Private ocr = New IronTesseract()



' Utilize using statement for automatic disposal of OcrInput object after usage

Using input = New OcrInput()

	' Set a title for the OCR input, useful for identifying the content in larger projects

	input.Title = "Pdf Title"



	' Define the page indices of the images that are to be processed

	Dim pageIndices = New Integer() { 1, 2 }



	' Load images from the specified TIFF file, using the defined page indices

	input.LoadImageFrames("example.tiff", pageIndices)



	' Perform OCR on the input and store the result

	Dim result As OcrResult = ocr.Read(input)



	' Save the OCR result as a searchable PDF document

	result.SaveAsSearchablePdf("searchable.pdf")

End Using

using IronOcr;

// Instantiate the OCR engine
var ocr = new IronTesseract();

// Using block to properly dispose of OcrInput resources
using (var input = new OcrInput())
{
    // Set a title for the OCR input
    input.Title = "Html Title";

    // Load images and PDFs for OCR processing
    input.AddImage("image2.jpeg");

    // The LoadPdf method requires a file and can include a password for encrypted PDFs
    input.AddPdf("example.pdf", "password");

    // Load specific frames from a TIFF image using page indices
    var pageIndices = new int[] { 1, 2 };
    input.AddTiff("example.tiff", pageIndices);

    // Perform OCR on the provided input and obtain the result
    OcrResult result = ocr.Read(input);

    // Save the result as a HOCR file, which is a format for representing OCR results
    result.SaveAsHocrFile("hocr.html");
}

Imports IronOcr



' Instantiate the OCR engine

Private ocr = New IronTesseract()



' Using block to properly dispose of OcrInput resources

Using input = New OcrInput()

	' Set a title for the OCR input

	input.Title = "Html Title"



	' Load images and PDFs for OCR processing

	input.AddImage("image2.jpeg")



	' The LoadPdf method requires a file and can include a password for encrypted PDFs

	input.AddPdf("example.pdf", "password")



	' Load specific frames from a TIFF image using page indices

	Dim pageIndices = New Integer() { 1, 2 }

	input.AddTiff("example.tiff", pageIndices)



	' Perform OCR on the provided input and obtain the result

	Dim result As OcrResult = ocr.Read(input)



	' Save the result as a HOCR file, which is a format for representing OCR results

	result.SaveAsHocrFile("hocr.html")

End Using

// Include the IronOcr namespace to use IronTesseract for OCR and barcode reading.
using IronOcr;

// Create a new instance of IronTesseract for performing optical character and barcode recognition.
var ocr = new IronTesseract();

// Enable barcode reading in the OCR engine's configuration.
ocr.Configuration.ReadBarCodes = true;

// The OcrInput class allows for the loading of images which are to be processed by the OCR engine.
using (var input = new OcrInput())
{
    // Load an image file into the OcrInput. Ensure the path is accurate relative to the execution directory.
    // The image should contain a barcode or text for OCR.
    input.AddImage("img/Barcode.png");

    // Perform OCR and barcode reading on the input image.
    // The Read method returns an OcrResult containing recognized text, barcodes, and more.
    var result = ocr.Read(input);

    // Iterate through the detected barcodes in the OcrResult.
    foreach (var barcode in result.Barcodes)
    {
        // Output the barcode value to the console.
        Console.WriteLine($"Barcode Value: {barcode.Value}");

        // Additional barcode properties, such as type and location, can be accessed as needed.
        Console.WriteLine($"Type: {barcode.Type}, Location: {barcode.Location}");
    }
}

' Include the IronOcr namespace to use IronTesseract for OCR and barcode reading.

Imports IronOcr



' Create a new instance of IronTesseract for performing optical character and barcode recognition.

Private ocr = New IronTesseract()



' Enable barcode reading in the OCR engine's configuration.

ocr.Configuration.ReadBarCodes = True



' The OcrInput class allows for the loading of images which are to be processed by the OCR engine.

Using input = New OcrInput()

	' Load an image file into the OcrInput. Ensure the path is accurate relative to the execution directory.

	' The image should contain a barcode or text for OCR.

	input.AddImage("img/Barcode.png")



	' Perform OCR and barcode reading on the input image.

	' The Read method returns an OcrResult containing recognized text, barcodes, and more.

	Dim result = ocr.Read(input)



	' Iterate through the detected barcodes in the OcrResult.

	For Each barcode In result.Barcodes

		' Output the barcode value to the console.

		Console.WriteLine($"Barcode Value: {barcode.Value}")



		' Additional barcode properties, such as type and location, can be accessed as needed.

		Console.WriteLine($"Type: {barcode.Type}, Location: {barcode.Location}")

	Next barcode

End Using

using System;
using IronOcr;
using IronSoftware.Drawing;

// Instantiate the IronTesseract OCR engine
IronTesseract ocr = new IronTesseract
{
    // Enable reading of barcodes in the OCR process
    Configuration = { ReadBarCodes = true }
};

// Create an OCR input object to hold the images to be analyzed
using OcrInput input = new OcrInput();

// Specify the page indexes of the TIFF file to be processed (pages 1 and 2)
int[] pageIndices = { 1, 2 };
input.LoadImageFrames(@"img\Potter.tiff", pageIndices);

// Process the input images and obtain the OCR result
OcrResult result = ocr.Read(input);

// Iterate through each page in the OCR result
foreach (var page in result.Pages)
{
    // Fetch information about the current page
    int pageNumber = page.PageNumber;
    string pageText = page.Text;
    int pageWordCount = page.WordCount;

    // Obtain barcodes if any are present on the page
    OcrResult.Barcode[] barcodes = page.Barcodes;

    // Convert the page content into images, supporting both AnyBitmap and System.Drawing.Bitmap types
    AnyBitmap pageImage = page.ToBitmap();
    System.Drawing.Bitmap pageImageLegacy = page.ToBitmap();
    double pageWidth = page.Width;
    double pageHeight = page.Height;

    // Iterate through each paragraph on the current page
    foreach (var paragraph in page.Paragraphs)
    {
        // Extract paragraph details
        int paragraphNumber = paragraph.ParagraphNumber;
        string paragraphText = paragraph.Text;
        System.Drawing.Bitmap paragraphImage = paragraph.ToBitmap();
        int paragraphXLocation = paragraph.X;
        int paragraphYLocation = paragraph.Y;
        int paragraphWidth = paragraph.Width;
        int paragraphHeight = paragraph.Height;
        double paragraphOcrAccuracy = paragraph.Confidence;
        var paragraphTextDirection = paragraph.TextDirection;

        // Iterate through each line within the current paragraph
        foreach (var line in paragraph.Lines)
        {
            // Extract line information
            int lineNumber = line.LineNumber;
            string lineText = line.Text;
            AnyBitmap lineImage = line.ToBitmap();
            System.Drawing.Bitmap lineImageLegacy = line.ToBitmap();
            int lineXLocation = line.X;
            int lineYLocation = line.Y;
            int lineWidth = line.Width;
            int lineHeight = line.Height;
            double lineOcrAccuracy = line.Confidence;
            double lineSkew = line.BaselineAngle;
            double lineOffset = line.BaselineOffset;

            // Iterate through each word in the line
            foreach (var word in line.Words)
            {
                int wordNumber = word.WordNumber;
                string wordText = word.Text;
                AnyBitmap wordImage = word.ToBitmap();
                System.Drawing.Image wordImageLegacy = word.ToBitmap();
                int wordXLocation = word.X;
                int wordYLocation = word.Y;
                int wordWidth = word.Width;
                int wordHeight = word.Height;
                double wordOcrAccuracy = word.Confidence;

                // Check for font details, available only when using certain Tesseract engine modes
                if (word.Font != null)
                {
                    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 fontIsCaligraphic = word.Font.IsCaligraphic;
                }

                // Iterate through each character in the word
                foreach (var character in word.Characters)
                {
                    int characterNumber = character.CharacterNumber;
                    string characterText = character.Text;
                    AnyBitmap characterImage = character.ToBitmap();
                    System.Drawing.Bitmap characterImageLegacy = character.ToBitmap();
                    int characterXLocation = character.X;
                    int characterYLocation = character.Y;
                    int characterWidth = character.Width;
                    int characterHeight = character.Height;
                    double characterOcrAccuracy = character.Confidence;

                    // Get alternative symbol choices and their probabilities, useful for spell checking
                    OcrResult.Choice[] characterChoices = character.Choices;
                }
            }
        }
    }
}

Imports System

Imports IronOcr

Imports IronSoftware.Drawing



' Instantiate the IronTesseract OCR engine

Private ocr As New IronTesseract With {

	.Configuration = { ReadBarCodes = True }

}



' Create an OCR input object to hold the images to be analyzed

Private OcrInput As using



' Specify the page indexes of the TIFF file to be processed (pages 1 and 2)

Private pageIndices() As Integer = { 1, 2 }

input.LoadImageFrames("img\Potter.tiff", pageIndices)



' Process the input images and obtain the OCR result

Dim result As OcrResult = ocr.Read(input)



' Iterate through each page in the OCR result

For Each page In result.Pages

	' Fetch information about the current page

	Dim pageNumber As Integer = page.PageNumber

	Dim pageText As String = page.Text

	Dim pageWordCount As Integer = page.WordCount



	' Obtain barcodes if any are present on the page

	Dim barcodes() As OcrResult.Barcode = page.Barcodes



	' Convert the page content into images, supporting both AnyBitmap and System.Drawing.Bitmap types

	Dim pageImage As AnyBitmap = page.ToBitmap()

	Dim pageImageLegacy As System.Drawing.Bitmap = page.ToBitmap()

	Dim pageWidth As Double = page.Width

	Dim pageHeight As Double = page.Height



	' Iterate through each paragraph on the current page

	For Each paragraph In page.Paragraphs

		' Extract paragraph details

		Dim paragraphNumber As Integer = paragraph.ParagraphNumber

		Dim paragraphText As String = paragraph.Text

		Dim paragraphImage As System.Drawing.Bitmap = paragraph.ToBitmap()

		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



		' Iterate through each line within the current paragraph

		For Each line In paragraph.Lines

			' Extract line information

			Dim lineNumber As Integer = line.LineNumber

			Dim lineText As String = line.Text

			Dim lineImage As AnyBitmap = line.ToBitmap()

			Dim lineImageLegacy As System.Drawing.Bitmap = line.ToBitmap()

			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



			' Iterate through each word in the line

			For Each word In line.Words

				Dim wordNumber As Integer = word.WordNumber

				Dim wordText As String = word.Text

				Dim wordImage As AnyBitmap = word.ToBitmap()

				Dim wordImageLegacy As System.Drawing.Image = word.ToBitmap()

				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



				' Check for font details, available only when using certain Tesseract engine modes

				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 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



				' Iterate through each character in the word

				For Each character In word.Characters

					Dim characterNumber As Integer = character.CharacterNumber

					Dim characterText As String = character.Text

					Dim characterImage As AnyBitmap = character.ToBitmap()

					Dim characterImageLegacy As System.Drawing.Bitmap = character.ToBitmap()

					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



					' Get alternative symbol choices and their probabilities, useful for spell checking

					Dim characterChoices() As OcrResult.Choice = character.Choices

				Next character

			Next word

		Next line

	Next paragraph

Next page