Introducción al OCR en C# y VB.NET

string Text = new IronTesseract().Read(@"img\Screenshot.png").Text;

Dim Text As String = (New IronTesseract()).Read("img\Screenshot.png").Text

using IronOcr;

IronTesseract ocr = new IronTesseract();
using OcrInput input = new OcrInput();

// Add multiple images
input.LoadImage("images/sample.jpeg");

OcrResult result = ocr.Read(input);
Console.WriteLine(result.Text);

Imports IronOcr

Private ocr As New IronTesseract()
Private OcrInput As using

' Add multiple images
input.LoadImage("images/sample.jpeg")

Dim result As OcrResult = ocr.Read(input)
Console.WriteLine(result.Text)

using IronOcr;

IronTesseract ocr = new IronTesseract();
using OcrInput input = new OcrInput();

// We can also select specific PDF page numbers to OCR
input.LoadPdf("example.pdf", Password: "password");

OcrResult result = ocr.Read(input);
Console.WriteLine(result.Text);

// 1 page for every page of the PDF
Console.WriteLine($"{result.Pages.Length} Pages");

Imports IronOcr

Private ocr As New IronTesseract()
Private OcrInput As using

' We can also select specific PDF page numbers to OCR
input.LoadPdf("example.pdf", Password:= "password")

Dim result As OcrResult = ocr.Read(input)
Console.WriteLine(result.Text)

' 1 page for every page of the PDF
Console.WriteLine($"{result.Pages.Length} Pages")

using IronOcr;

IronTesseract ocr = new IronTesseract();
using OcrInput input = new OcrInput();
var pageindices = new int[] { 1, 2 };
input.LoadImageFrames("multi-frame.tiff", pageindices);
OcrResult result = ocr.Read(input);
Console.WriteLine(result.Text);

Imports IronOcr

Private ocr As New IronTesseract()
Private OcrInput As using
Private pageindices = New Integer() { 1, 2 }
input.LoadImageFrames("multi-frame.tiff", pageindices)
Dim result As OcrResult = ocr.Read(input)
Console.WriteLine(result.Text)

using IronOcr;

IronTesseract ocr = new IronTesseract();
ocr.Configuration.ReadBarCodes = true;

using OcrInput input = new OcrInput();
input.LoadImage("img/Barcode.png");

OcrResult Result = ocr.Read(input);
foreach (var Barcode in Result.Barcodes)
{
    // type and location properties also exposed
    Console.WriteLine(Barcode.Value);
}

Imports IronOcr

Private ocr As New IronTesseract()
ocr.Configuration.ReadBarCodes = True

Using input As New OcrInput()
	input.LoadImage("img/Barcode.png")
	
	Dim Result As OcrResult = ocr.Read(input)
	For Each Barcode In Result.Barcodes
		' type and location properties also exposed
		Console.WriteLine(Barcode.Value)
	Next Barcode
End Using

using IronOcr;

IronTesseract ocr = new IronTesseract();
using OcrInput input = new OcrInput();

// Dimensions are in pixel
var contentArea = new System.Drawing.Rectangle() { X = 215, Y = 1250, Height = 280, Width = 1335 };

input.LoadImage("document.png", contentArea);

OcrResult result = ocr.Read(input);
Console.WriteLine(result.Text);

Imports IronOcr

Private ocr As New IronTesseract()
Private OcrInput As using

' Dimensions are in pixel
Private contentArea = New System.Drawing.Rectangle() With {
	.X = 215,
	.Y = 1250,
	.Height = 280,
	.Width = 1335
}

input.LoadImage("document.png", contentArea)

Dim result As OcrResult = ocr.Read(input)
Console.WriteLine(result.Text)

using IronOcr;

IronTesseract ocr = new IronTesseract();
using OcrInput input = new OcrInput();
var pageindices = new int[] { 1, 2 };
input.LoadImageFrames(@"img\Potter.tiff", pageindices);

// fixes digital noise and poor scanning
input.DeNoise();

// fixes rotation and perspective
input.Deskew();

OcrResult result = ocr.Read(input);
Console.WriteLine(result.Text);

Imports IronOcr

Private ocr As New IronTesseract()
Private OcrInput As using
Private pageindices = New Integer() { 1, 2 }
input.LoadImageFrames("img\Potter.tiff", pageindices)

' fixes digital noise and poor scanning
input.DeNoise()

' fixes rotation and perspective
input.Deskew()

Dim result As OcrResult = ocr.Read(input)
Console.WriteLine(result.Text)

using IronOcr;

IronTesseract ocr = new IronTesseract();
using OcrInput input = new OcrInput();
input.Title = "Quarterly Report";
input.LoadImage("image1.jpeg");
input.LoadImage("image2.png");
var pageindices = new int[] { 1, 2 };
input.LoadImageFrames("image3.gif", pageindices);

OcrResult result = ocr.Read(input);
result.SaveAsSearchablePdf("searchable.pdf");

Imports IronOcr

Private ocr As New IronTesseract()
Private OcrInput As using
input.Title = "Quarterly Report"
input.LoadImage("image1.jpeg")
input.LoadImage("image2.png")
Dim pageindices = New Integer() { 1, 2 }
input.LoadImageFrames("image3.gif", pageindices)

Dim result As OcrResult = ocr.Read(input)
result.SaveAsSearchablePdf("searchable.pdf")

using IronOcr;

IronTesseract ocr = new IronTesseract();
using OcrInput input = new OcrInput();
var pageindices = new int[] { 1, 2 };
input.LoadImageFrames("example.tiff", pageindices);
ocr.Read(input).SaveAsSearchablePdf("searchable.pdf");

Imports IronOcr

Private ocr As New IronTesseract()
Private OcrInput As using
Private pageindices = New Integer() { 1, 2 }
input.LoadImageFrames("example.tiff", pageindices)
ocr.Read(input).SaveAsSearchablePdf("searchable.pdf")

using IronOcr;

IronTesseract ocr = new IronTesseract();
using OcrInput input = new OcrInput();
input.Title = "Html Title";
input.LoadImage("image1.jpeg");

OcrResult Result = ocr.Read(input);
Result.SaveAsHocrFile("results.html");

Imports IronOcr

Private ocr As New IronTesseract()
Private OcrInput As using
input.Title = "Html Title"
input.LoadImage("image1.jpeg")

Dim Result As OcrResult = ocr.Read(input)
Result.SaveAsHocrFile("results.html")

using IronOcr;

IronTesseract ocr = new IronTesseract();
using OcrInput input = new OcrInput();
input.LoadImage("LowQuality.jpeg");

// fixes digital noise and poor scanning
input.DeNoise();

// fixes rotation and perspective
input.Deskew();

OcrResult result = ocr.Read(input);
Console.WriteLine(result.Text);

Imports IronOcr

Private ocr As New IronTesseract()
Private OcrInput As using
input.LoadImage("LowQuality.jpeg")

' fixes digital noise and poor scanning
input.DeNoise()

' fixes rotation and perspective
input.Deskew()

Dim result As OcrResult = ocr.Read(input)
Console.WriteLine(result.Text)

// Reference to the path of the source file that demonstrates setting language packs for OCR
using IronOcr;

// PM> Install IronOcr.Languages.Arabic
IronTesseract ocr = new IronTesseract();
ocr.Language = OcrLanguage.Arabic;

using OcrInput input = new OcrInput();

var pageindices = new int[] { 1, 2 };
input.LoadImageFrames("img/arabic.gif", pageindices);
// Add image filters if needed
// In this case, even thought input is very low quality
// IronTesseract can read what conventional Tesseract cannot.
OcrResult result = ocr.Read(input);
// Console can't print Arabic on Windows easily.
// Let's save to disk instead.
result.SaveAsTextFile("arabic.txt");

' Reference to the path of the source file that demonstrates setting language packs for OCR
Imports IronOcr

' PM> Install IronOcr.Languages.Arabic
Private ocr As New IronTesseract()
ocr.Language = OcrLanguage.Arabic

Using input As New OcrInput()
	
	Dim pageindices = New Integer() { 1, 2 }
	input.LoadImageFrames("img/arabic.gif", pageindices)
	' Add image filters if needed
	' In this case, even thought input is very low quality
	' IronTesseract can read what conventional Tesseract cannot.
	Dim result As OcrResult = ocr.Read(input)
	' Console can't print Arabic on Windows easily.
	' Let's save to disk instead.
	result.SaveAsTextFile("arabic.txt")
End Using