C# Tesseract OCR 示例

using IronOcr;
using System;

var ocr = new IronTesseract();

// Hundreds of languages available
ocr.Language = OcrLanguage.English;

using var input = new OcrInput();
var pageindices = new int[] { 1, 2 };
input.LoadImageFrames(@"img\example.tiff", pageindices);
// input.DeNoise();  optional filter
// input.Deskew();   optional filter

OcrResult result = ocr.Read(input);
Console.WriteLine(result.Text);
// Explore the OcrResult using IntelliSense

Imports IronOcr
Imports System

Private ocr = New IronTesseract()

' Hundreds of languages available
ocr.Language = OcrLanguage.English

Dim input = New OcrInput()
Dim pageindices = New Integer() { 1, 2 }
input.LoadImageFrames("img\example.tiff", pageindices)
' input.DeNoise();  optional filter
' input.Deskew();   optional filter

Dim result As OcrResult = ocr.Read(input)
Console.WriteLine(result.Text)
' Explore the OcrResult using IntelliSense

using IronOcr;
using System;

var ocr = new IronTesseract();
using var input = new OcrInput();
var pageindices = new int[] { 1, 2 };
input.LoadImageFrames(@"img\example.tiff", pageindices);
input.DeNoise();  //fixes digital noise
input.Deskew();   //fixes rotation and perspective

// there are dozens more filters, but most users wont need them
OcrResult result = ocr.Read(input);
Console.WriteLine(result.Text);

Imports IronOcr
Imports System

Private ocr = New IronTesseract()
Private input = New OcrInput()
Private pageindices = New Integer() { 1, 2 }
input.LoadImageFrames("img\example.tiff", pageindices)
input.DeNoise() 'fixes digital noise
input.Deskew() 'fixes rotation and perspective

' there are dozens more filters, but most users wont need them
Dim result As OcrResult = ocr.Read(input)
Console.WriteLine(result.Text)

using IronOcr;
using System;

var ocr = new IronTesseract();
using var input = new OcrInput();
input.LoadPdf("example.pdf", Password: "password");
var pageindices = new int[] { 1, 2 };
input.LoadImageFrames("multi-frame.tiff", pageindices);
input.LoadImage("image1.png");
input.LoadImage("image2.jpeg");
//... many more

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

Imports IronOcr
Imports System

Private ocr = New IronTesseract()
Private input = New OcrInput()
input.LoadPdf("example.pdf", Password:= "password")
Dim pageindices = New Integer() { 1, 2 }
input.LoadImageFrames("multi-frame.tiff", pageindices)
input.LoadImage("image1.png")
input.LoadImage("image2.jpeg")
'... many more

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

using IronOcr;
using System;

var ocr = new IronTesseract();

// Configure for speed.  35% faster and only 0.2% loss of accuracy
ocr.Configuration.BlackListCharacters = "~`$#^*_}{][|\\@¢©«»°±·×‑–—‘’“”•…′″€™←↑→↓↔⇄⇒∅∼≅≈≠≤≥≪≫⌁⌘○◔◑◕●☐☑☒☕☮☯☺♡⚓✓✰";
ocr.Configuration.PageSegmentationMode = TesseractPageSegmentationMode.Auto;
ocr.Configuration.ReadBarCodes = false;
ocr.Language = OcrLanguage.EnglishFast;

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

Imports IronOcr
Imports System

Private ocr = New IronTesseract()

' Configure for speed.  35% faster and only 0.2% loss of accuracy
ocr.Configuration.BlackListCharacters = "~`$#^*_}{][|\@¢©«»°±·×‑–—‘’“”•…′″€™←↑→↓↔⇄⇒∅∼≅≈≠≤≥≪≫⌁⌘○◔◑◕●☐☑☒☕☮☯☺♡⚓✓✰"
ocr.Configuration.PageSegmentationMode = TesseractPageSegmentationMode.Auto
ocr.Configuration.ReadBarCodes = False
ocr.Language = OcrLanguage.EnglishFast

Dim input = New OcrInput()
Dim pageindices = New Integer() { 1, 2 }
input.LoadImageFrames("img\Potter.tiff", pageindices)
Dim result = ocr.Read(input)
Console.WriteLine(result.Text)

using IronOcr;

var text = new IronTesseract().Read("img.png").Text;

Imports IronOcr

Private text = (New IronTesseract()).Read("img.png").Text

using IronOcr;

var ocr = new IronTesseract();
ocr.Language = OcrLanguage.Arabic;

using var 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.

var result = ocr.Read(input);

// Console can't print Arabic on Windows easily.
// Let's save to disk instead.
result.SaveAsTextFile("arabic.txt");

Imports IronOcr

Private ocr = New IronTesseract()
ocr.Language = OcrLanguage.Arabic

Dim input = 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 = ocr.Read(input)

' Console can't print Arabic on Windows easily.
' Let's save to disk instead.
result.SaveAsTextFile("arabic.txt")

using IronOcr;

// For the Chinese Language Pack:
// PM> Install IronOcr.Languages.ChineseSimplified

var ocr = new IronTesseract();
ocr.Language = OcrLanguage.ChineseSimplified;
ocr.AddSecondaryLanguage(OcrLanguage.English);

// We can add any number of languages
using var input = new OcrInput();
input.LoadPdf("multi-language.pdf");
var result = ocr.Read(input);
result.SaveAsTextFile("results.txt");

Imports IronOcr

' For the Chinese Language Pack:
' PM> Install IronOcr.Languages.ChineseSimplified

Private ocr = New IronTesseract()
ocr.Language = OcrLanguage.ChineseSimplified
ocr.AddSecondaryLanguage(OcrLanguage.English)

' We can add any number of languages
Dim input = New OcrInput()
input.LoadPdf("multi-language.pdf")
Dim result = ocr.Read(input)
result.SaveAsTextFile("results.txt")