Tutorial de OCR de imagen a texto en C#: Convertir imágenes a texto sin Tesseract

// Basic C# OCR image to text conversion using IronOCR
// This example shows how to extract text from images without complex setup

using IronOcr;
using System;

try
{
    // Initialize IronTesseract for OCR operations
    var ocrEngine = new IronTesseract();

    // Path to your image file - supports PNG, JPG, TIFF, BMP, and more
    var imagePath = @"img\Screenshot.png";

    // Create input and perform OCR to convert image to text
    using (var input = new OcrInput(imagePath))
    {
        // Read text from image and get results
        OcrResult result = ocrEngine.Read(input);

        // Display extracted text
        Console.WriteLine(result.Text);
    }
}
catch (OcrException ex)
{
    // Handle OCR-specific errors
    Console.WriteLine($"OCR Error: {ex.Message}");
}
catch (Exception ex)
{
    // Handle general errors
    Console.WriteLine($"Error: {ex.Message}");
}

' Basic C# OCR image to text conversion using IronOCR
' This example shows how to extract text from images without complex setup

Imports IronOcr
Imports System

Try
	' Initialize IronTesseract for OCR operations
	Dim ocrEngine = New IronTesseract()

	' Path to your image file - supports PNG, JPG, TIFF, BMP, and more
	Dim imagePath = "img\Screenshot.png"

	' Create input and perform OCR to convert image to text
	Using input = New OcrInput(imagePath)
		' Read text from image and get results
		Dim result As OcrResult = ocrEngine.Read(input)

		' Display extracted text
		Console.WriteLine(result.Text)
	End Using
Catch ex As OcrException
	' Handle OCR-specific errors
	Console.WriteLine($"OCR Error: {ex.Message}")
Catch ex As Exception
	' Handle general errors
	Console.WriteLine($"Error: {ex.Message}")
End Try

// Multi-source document processing
using IronOcr;

IronTesseract ocr = new IronTesseract();

using (OcrInput input = new OcrInput())
{
    // Add various image formats
    input.AddImage("image1.jpeg");
    input.AddImage("image2.png");

    // Process specific frames from multi-frame images
    int[] frameNumbers = { 1, 2 };
    input.AddImageFrames("image3.gif", frameNumbers);

    // Process all sources together
    OcrResult result = ocr.Read(input);

    // Verify page count
    Console.WriteLine($"{result.Pages.Count} Pages processed.");
}

' Multi-source document processing
Imports IronOcr

Private ocr As New IronTesseract()

Using input As New OcrInput()
	' Add various image formats
	input.AddImage("image1.jpeg")
	input.AddImage("image2.png")

	' Process specific frames from multi-frame images
	Dim frameNumbers() As Integer = { 1, 2 }
	input.AddImageFrames("image3.gif", frameNumbers)

	' Process all sources together
	Dim result As OcrResult = ocr.Read(input)

	' Verify page count
	Console.WriteLine($"{result.Pages.Count} Pages processed.")
End Using

using IronOcr;

IronTesseract ocr = new IronTesseract();

using (OcrInput input = new OcrInput())
{
    // Define pages to process (0-based indexing)
    int[] pageIndices = new int[] { 0, 1 };

    // Load specific TIFF frames
    input.LoadImageFrames("MultiFrame.Tiff", pageIndices);

    // Extract text from all frames
    OcrResult result = ocr.Read(input);

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

Imports IronOcr

Private ocr As New IronTesseract()

Using input As New OcrInput()
	' Define pages to process (0-based indexing)
	Dim pageIndices() As Integer = { 0, 1 }

	' Load specific TIFF frames
	input.LoadImageFrames("MultiFrame.Tiff", pageIndices)

	' Extract text from all frames
	Dim result As OcrResult = ocr.Read(input)

	Console.WriteLine(result.Text)
	Console.WriteLine($"{result.Pages.Count} Pages processed")
End Using

using System;
using IronOcr;

IronTesseract ocr = new IronTesseract();

using (OcrInput input = new OcrInput())
{
    try
    {
        // Load password-protected PDF if needed
        input.LoadPdf("example.pdf", "password");

        // Process entire document
        OcrResult result = ocr.Read(input);

        Console.WriteLine(result.Text);
        Console.WriteLine($"{result.Pages.Count} Pages recognized");
    }
    catch (Exception ex)
    {
        Console.WriteLine($"Error processing PDF: {ex.Message}");
    }
}

Imports System
Imports IronOcr

Private ocr As New IronTesseract()

Using input As New OcrInput()
	Try
		' Load password-protected PDF if needed
		input.LoadPdf("example.pdf", "password")

		' Process entire document
		Dim result As OcrResult = ocr.Read(input)

		Console.WriteLine(result.Text)
		Console.WriteLine($"{result.Pages.Count} Pages recognized")
	Catch ex As Exception
		Console.WriteLine($"Error processing PDF: {ex.Message}")
	End Try
End Using

using IronOcr;

IronTesseract ocr = new IronTesseract();

using (OcrInput input = new OcrInput())
{
    // Set document metadata
    input.Title = "Quarterly Report";

    // Combine multiple sources
    input.AddImage("image1.jpeg");
    input.AddImage("image2.png");

    // Add specific frames from animated images
    int[] gifFrames = new int[] { 1, 2 };
    input.AddImageFrames("image3.gif", gifFrames);

    // Create searchable PDF
    OcrResult result = ocr.Read(input);
    result.SaveAsSearchablePdf("searchable.pdf");
}

Imports IronOcr

Private ocr As New IronTesseract()

Using input As New OcrInput()
	' Set document metadata
	input.Title = "Quarterly Report"

	' Combine multiple sources
	input.AddImage("image1.jpeg")
	input.AddImage("image2.png")

	' Add specific frames from animated images
	Dim gifFrames() As Integer = { 1, 2 }
	input.AddImageFrames("image3.gif", gifFrames)

	' Create searchable PDF
	Dim result As OcrResult = ocr.Read(input)
	result.SaveAsSearchablePdf("searchable.pdf")
End Using

using IronOcr;

var ocr = new IronTesseract();

using (var input = new OcrInput())
{
    // Set PDF metadata
    input.Title = "Annual Report 2024";

    // Process existing PDF
    input.LoadPdf("example.pdf", "password");

    // Generate searchable version
    var result = ocr.Read(input);
    result.SaveAsSearchablePdf("searchable.pdf");
}

Imports IronOcr

Private ocr = New IronTesseract()

Using input = New OcrInput()
	' Set PDF metadata
	input.Title = "Annual Report 2024"

	' Process existing PDF
	input.LoadPdf("example.pdf", "password")

	' Generate searchable version
	Dim result = ocr.Read(input)
	result.SaveAsSearchablePdf("searchable.pdf")
End Using

using IronOcr;

var ocr = new IronTesseract();

using (var input = new OcrInput())
{
    // Configure document properties
    input.Title = "Scanned Archive Document";

    // Select pages to process
    var pageIndices = new int[] { 1, 2 };
    input.LoadImageFrames("example.tiff", pageIndices);

    // Create searchable PDF from TIFF
    OcrResult result = ocr.Read(input);
    result.SaveAsSearchablePdf("searchable.pdf");
}

Imports IronOcr

Private ocr = New IronTesseract()

Using input = New OcrInput()
	' Configure document properties
	input.Title = "Scanned Archive Document"

	' Select pages to process
	Dim pageIndices = New Integer() { 1, 2 }
	input.LoadImageFrames("example.tiff", pageIndices)

	' Create searchable PDF from TIFF
	Dim result As OcrResult = ocr.Read(input)
	result.SaveAsSearchablePdf("searchable.pdf")
End Using

using IronOcr;

var ocr = new IronTesseract();

using (var input = new OcrInput())
{
    // Set HTML title
    input.Title = "Document Archive";

    // Process multiple document types
    input.AddImage("image2.jpeg");
    input.AddPdf("example.pdf", "password");

    // Add TIFF pages
    var pageIndices = new int[] { 1, 2 };
    input.AddTiff("example.tiff", pageIndices);

    // Export as HOCR with position data
    OcrResult result = ocr.Read(input);
    result.SaveAsHocrFile("hocr.html");
}

Imports IronOcr

Private ocr = New IronTesseract()

Using input = New OcrInput()
	' Set HTML title
	input.Title = "Document Archive"

	' Process multiple document types
	input.AddImage("image2.jpeg")
	input.AddPdf("example.pdf", "password")

	' Add TIFF pages
	Dim pageIndices = New Integer() { 1, 2 }
	input.AddTiff("example.tiff", pageIndices)

	' Export as HOCR with position data
	Dim result As OcrResult = ocr.Read(input)
	result.SaveAsHocrFile("hocr.html")
End Using

// Enable combined text and barcode recognition
using IronOcr;

var ocr = new IronTesseract();

// Enable barcode detection
ocr.Configuration.ReadBarCodes = true;

using (var input = new OcrInput())
{
    // Load image containing both text and barcodes
    input.AddImage("img/Barcode.png");

    // Process both text and barcodes
    var result = ocr.Read(input);

    // Extract barcode data
    foreach (var barcode in result.Barcodes)
    {
        Console.WriteLine($"Barcode Value: {barcode.Value}");
        Console.WriteLine($"Type: {barcode.Type}, Location: {barcode.Location}");
    }
}

' Enable combined text and barcode recognition
Imports IronOcr

Private ocr = New IronTesseract()

' Enable barcode detection
ocr.Configuration.ReadBarCodes = True

Using input = New OcrInput()
	' Load image containing both text and barcodes
	input.AddImage("img/Barcode.png")

	' Process both text and barcodes
	Dim result = ocr.Read(input)

	' Extract barcode data
	For Each barcode In result.Barcodes
		Console.WriteLine($"Barcode Value: {barcode.Value}")
		Console.WriteLine($"Type: {barcode.Type}, Location: {barcode.Location}")
	Next barcode
End Using

using System;
using IronOcr;
using IronSoftware.Drawing;

// Configure with barcode support
IronTesseract ocr = new IronTesseract
{
    Configuration = { ReadBarCodes = true }
};

using OcrInput input = new OcrInput();

// Process multi-page document
int[] pageIndices = { 1, 2 };
input.LoadImageFrames(@"img\Potter.tiff", pageIndices);

OcrResult result = ocr.Read(input);

// Navigate the complete results hierarchy
foreach (var page in result.Pages)
{
    // Page-level data
    int pageNumber = page.PageNumber;
    string pageText = page.Text;
    int pageWordCount = page.WordCount;

    // Extract page elements
    OcrResult.Barcode[] barcodes = page.Barcodes;
    AnyBitmap pageImage = page.ToBitmap();
    double pageWidth = page.Width;
    double pageHeight = page.Height;

    foreach (var paragraph in page.Paragraphs)
    {
        // Paragraph properties
        int paragraphNumber = paragraph.ParagraphNumber;
        string paragraphText = paragraph.Text;
        double paragraphConfidence = paragraph.Confidence;
        var textDirection = paragraph.TextDirection;

        foreach (var line in paragraph.Lines)
        {
            // Line details including baseline information
            string lineText = line.Text;
            double lineConfidence = line.Confidence;
            double baselineAngle = line.BaselineAngle;
            double baselineOffset = line.BaselineOffset;

            foreach (var word in line.Words)
            {
                // Word-level data
                string wordText = word.Text;
                double wordConfidence = word.Confidence;

                // Font information (when available)
                if (word.Font != null)
                {
                    string fontName = word.Font.FontName;
                    double fontSize = word.Font.FontSize;
                    bool isBold = word.Font.IsBold;
                    bool isItalic = word.Font.IsItalic;
                }

                foreach (var character in word.Characters)
                {
                    // Character-level analysis
                    string charText = character.Text;
                    double charConfidence = character.Confidence;

                    // Alternative character choices for spell-checking
                    OcrResult.Choice[] alternatives = character.Choices;
                }
            }
        }
    }
}

Imports System
Imports IronOcr
Imports IronSoftware.Drawing

' Configure with barcode support
Private ocr As New IronTesseract With {
	.Configuration = { ReadBarCodes = True }
}

Private OcrInput As using

' Process multi-page document
Private pageIndices() As Integer = { 1, 2 }
input.LoadImageFrames("img\Potter.tiff", pageIndices)

Dim result As OcrResult = ocr.Read(input)

' Navigate the complete results hierarchy
For Each page In result.Pages
	' Page-level data
	Dim pageNumber As Integer = page.PageNumber
	Dim pageText As String = page.Text
	Dim pageWordCount As Integer = page.WordCount

	' Extract page elements
	Dim barcodes() As OcrResult.Barcode = page.Barcodes
	Dim pageImage As AnyBitmap = page.ToBitmap()
	Dim pageWidth As Double = page.Width
	Dim pageHeight As Double = page.Height

	For Each paragraph In page.Paragraphs
		' Paragraph properties
		Dim paragraphNumber As Integer = paragraph.ParagraphNumber
		Dim paragraphText As String = paragraph.Text
		Dim paragraphConfidence As Double = paragraph.Confidence
		Dim textDirection = paragraph.TextDirection

		For Each line In paragraph.Lines
			' Line details including baseline information
			Dim lineText As String = line.Text
			Dim lineConfidence As Double = line.Confidence
			Dim baselineAngle As Double = line.BaselineAngle
			Dim baselineOffset As Double = line.BaselineOffset

			For Each word In line.Words
				' Word-level data
				Dim wordText As String = word.Text
				Dim wordConfidence As Double = word.Confidence

				' Font information (when available)
				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 isItalic As Boolean = word.Font.IsItalic
				End If

				For Each character In word.Characters
					' Character-level analysis
					Dim charText As String = character.Text
					Dim charConfidence As Double = character.Confidence

					' Alternative character choices for spell-checking
					Dim alternatives() As OcrResult.Choice = character.Choices
				Next character
			Next word
		Next line
	Next paragraph
Next page