文字起こし・テキスト抽出のためにC#でストリームから読み取る方法

using IronOcr;
using IronSoftware.Drawing;

// Instantiate IronTesseract
IronTesseract ocrTesseract = new IronTesseract();

// Read image file to AnyBitmap
AnyBitmap anyBitmap = AnyBitmap.FromFile("Potter.tiff");

// Import image stream
using var imageInput = new OcrImageInput(anyBitmap.GetStream());
// Perform OCR
OcrResult ocrResult = ocrTesseract.Read(imageInput);

Imports IronOcr
Imports IronSoftware.Drawing

' Instantiate IronTesseract
Private ocrTesseract As New IronTesseract()

' Read image file to AnyBitmap
Private anyBitmap As AnyBitmap = AnyBitmap.FromFile("Potter.tiff")

' Import image stream
Private imageInput = New OcrImageInput(anyBitmap.GetStream())
' Perform OCR
Private ocrResult As OcrResult = ocrTesseract.Read(imageInput)

using IronOcr;
using IronSoftware.Drawing;
using System;

// Instantiate IronTesseract
IronTesseract ocrTesseract = new IronTesseract();

// Read image file to AnyBitmap
AnyBitmap anyBitmap = AnyBitmap.FromFile("Potter.tiff");

// Specify crop region
Rectangle scanRegion = new Rectangle(800, 200, 900, 400);

// Add image
using var imageInput = new OcrImageInput(anyBitmap.GetStream(), ContentArea: scanRegion);
// Perform OCR
OcrResult ocrResult = ocrTesseract.Read(imageInput);

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

Imports IronOcr
Imports IronSoftware.Drawing
Imports System

' Instantiate IronTesseract
Private ocrTesseract As New IronTesseract()

' Read image file to AnyBitmap
Private anyBitmap As AnyBitmap = AnyBitmap.FromFile("Potter.tiff")

' Specify crop region
Private scanRegion As New Rectangle(800, 200, 900, 400)

' Add image
Private imageInput = New OcrImageInput(anyBitmap.GetStream(), ContentArea:= scanRegion)
' Perform OCR
Private ocrResult As OcrResult = ocrTesseract.Read(imageInput)

' Output the result to console
Console.WriteLine(ocrResult.Text)

using IronOcr;
using IronSoftware.Drawing;
using System.IO;

// Process stream with filters
public string ProcessStreamWithFilters(Stream imageStream)
{
    IronTesseract ocrTesseract = new IronTesseract();

    // Configure for better accuracy
    ocrTesseract.Configuration.BlackListCharacters = "~`$#^*_}{][|\\";
    ocrTesseract.Configuration.PageSegmentationMode = TesseractPageSegmentationMode.AutoOsd;

    using var input = new OcrImageInput(imageStream);

    // Apply preprocessing filters
    input.Deskew();
    input.DeNoise();
    input.Sharpen();

    var result = ocrTesseract.Read(input);
    return result.Text;
}

Imports IronOcr
Imports IronSoftware.Drawing
Imports System.IO

' Process stream with filters
Public Function ProcessStreamWithFilters(imageStream As Stream) As String
    Dim ocrTesseract As New IronTesseract()

    ' Configure for better accuracy
    ocrTesseract.Configuration.BlackListCharacters = "~`$#^*_}{][|\"
    ocrTesseract.Configuration.PageSegmentationMode = TesseractPageSegmentationMode.AutoOsd

    Using input As New OcrImageInput(imageStream)
        ' Apply preprocessing filters
        input.Deskew()
        input.DeNoise()
        input.Sharpen()

        Dim result = ocrTesseract.Read(input)
        Return result.Text
    End Using
End Function

// Process stream and analyze results
using var input = new OcrImageInput(stream);
var result = new IronTesseract().Read(input);

// Access detailed results
foreach (var page in result.Pages)
{
    Console.WriteLine($"Page {page.PageNumber} Confidence: {page.Confidence}%");

    foreach (var paragraph in page.Paragraphs)
    {
        Console.WriteLine($"Paragraph: {paragraph.Text}");
        Console.WriteLine($"Location: X={paragraph.X}, Y={paragraph.Y}");
    }
}

// Export results
string text = result.Text;
string searchablePdf = result.SaveAsSearchablePdf("output.pdf");
string hocrHtml = result.SaveAsHocrHtml("output.html");

Imports IronOcr

' Process stream and analyze results
Using input As New OcrImageInput(stream)
    Dim result = New IronTesseract().Read(input)

    ' Access detailed results
    For Each page In result.Pages
        Console.WriteLine($"Page {page.PageNumber} Confidence: {page.Confidence}%")

        For Each paragraph In page.Paragraphs
            Console.WriteLine($"Paragraph: {paragraph.Text}")
            Console.WriteLine($"Location: X={paragraph.X}, Y={paragraph.Y}")
        Next
    Next

    ' Export results
    Dim text As String = result.Text
    Dim searchablePdf As String = result.SaveAsSearchablePdf("output.pdf")
    Dim hocrHtml As String = result.SaveAsHocrHtml("output.html")
End Using