OcrResult Class

VB C#

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();
var pages = new int[] { 1, 2 };
ocrInput.LoadImageFrames("example.tiff", pages);

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);
    double PageWidth = page.Width;
    double 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

Dim ocrInput As New OcrInput()
Dim pages = New Integer() { 1, 2 }
ocrInput.LoadImageFrames("example.tiff", pages)

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 Double = page.Width
	Dim PageHeight As Double = 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

Install-Package IronOcr

OcrResult Class

IronOCR returns an advanced result object for each page it scans using Tesseract 5. This contains location data, images, text, statistical confidence, alternative symbol choices, font-names, font-sizes decoration, font weights, and position for each:

Page
Paragraph
Line of Text
Word
Individual Character
Barcode

Here is an example of how you might retrieve and work with these data points using C# with IronOCR:

// Import the IronOCR library
using IronOcr;

class OCRExample
{
    static void Main()
    {
        // Create a new instance of the IronTesseract engine
        var OcrEngine = new IronTesseract();

        // Specify the file path of the scanned document
        var Input = new OcrInput(@"path_to_your_image_file.jpg");

        // Perform OCR on the input image
        OcrResult result = OcrEngine.Read(Input);

        // Check the number of pages detected
        Console.WriteLine($"Detected {result.Pages.Count} page(s)");

        // Iterate through each page
        foreach (var page in result.Pages)
        {
            // Output the page text
            Console.WriteLine($"Page Text: {page.Text}");

            // Iterate through each paragraph in the page
            foreach (var paragraph in page.Paragraphs)
            {
                Console.WriteLine($"Paragraph Text: {paragraph.Text}");

                // Iterate through each line in the paragraph
                foreach (var line in paragraph.Lines)
                {
                    Console.WriteLine($"Line Text: {line.Text}");

                    // Iterate through each word in the line
                    foreach (var word in line.Words)
                    {
                        Console.WriteLine($"Word Text: {word.Text}");

                        // Iterate through each character in the word
                        foreach (var character in word.Characters)
                        {
                            Console.WriteLine($"Character Text: {character.Text}");
                        }
                    }
                }
            }

            //Detect barcodes within the page and output their values
            foreach (var barcode in page.Barcodes)
            {
                Console.WriteLine($"Barcode Value: {barcode.Value}");
            }
        }
    }
}

// Import the IronOCR library
using IronOcr;

class OCRExample
{
    static void Main()
    {
        // Create a new instance of the IronTesseract engine
        var OcrEngine = new IronTesseract();

        // Specify the file path of the scanned document
        var Input = new OcrInput(@"path_to_your_image_file.jpg");

        // Perform OCR on the input image
        OcrResult result = OcrEngine.Read(Input);

        // Check the number of pages detected
        Console.WriteLine($"Detected {result.Pages.Count} page(s)");

        // Iterate through each page
        foreach (var page in result.Pages)
        {
            // Output the page text
            Console.WriteLine($"Page Text: {page.Text}");

            // Iterate through each paragraph in the page
            foreach (var paragraph in page.Paragraphs)
            {
                Console.WriteLine($"Paragraph Text: {paragraph.Text}");

                // Iterate through each line in the paragraph
                foreach (var line in paragraph.Lines)
                {
                    Console.WriteLine($"Line Text: {line.Text}");

                    // Iterate through each word in the line
                    foreach (var word in line.Words)
                    {
                        Console.WriteLine($"Word Text: {word.Text}");

                        // Iterate through each character in the word
                        foreach (var character in word.Characters)
                        {
                            Console.WriteLine($"Character Text: {character.Text}");
                        }
                    }
                }
            }

            //Detect barcodes within the page and output their values
            foreach (var barcode in page.Barcodes)
            {
                Console.WriteLine($"Barcode Value: {barcode.Value}");
            }
        }
    }
}

CONVERTER NOT RUNNING

$vbLabelText $csharpLabel

Explanation:

IronTesseract Engine: This is used to initiate the OCR process on the provided image input.
OcrInput: Represents the image file that will be processed. You need to specify the path to your image file.
Read Method: This processes the image and returns an OcrResult with all extracted data.
Iterating Structure: The example provided utilizes nested loops to dive deep from pages to characters and barcodes, allowing access to every element's text and properties.
Console Output: The program writes each text element to the console. Replace these actions with any function you need to perform using these elements.

This structured approach enables a detailed exploration and utilization of the various data points retrieved by IronOCR.