C#でのTesseract（テッセラクト）OCRを使った文字起こし・テキスト抽出

using IronOcr;
using System;

IronTesseract Ocr = new IronTesseract();

Ocr.Language = OcrLanguage.English;
Ocr.Configuration.PageSegmentationMode = TesseractPageSegmentationMode.AutoOsd;

// Configure Tesseract Engine
Ocr.Configuration.TesseractVariables["tessedit_parallelize"] = false;

using var input = new OcrInput();
input.LoadImage("/path/file.png");

OcrResult Result = Ocr.Read(input);
Console.WriteLine(Result.Text);

Imports IronOcr
Imports System

Private Ocr As New IronTesseract()

Ocr.Language = OcrLanguage.English
Ocr.Configuration.PageSegmentationMode = TesseractPageSegmentationMode.AutoOsd

' Configure Tesseract Engine
Ocr.Configuration.TesseractVariables("tessedit_parallelize") = False

Dim input = New OcrInput()
input.LoadImage("/path/file.png")

Dim Result As OcrResult = Ocr.Read(input)
Console.WriteLine(Result.Text)

// Example: Configure for financial documents
IronTesseract ocr = new IronTesseract
{
    Language = OcrLanguage.English,
    Configuration = new TesseractConfiguration
    {
        PageSegmentationMode = TesseractPageSegmentationMode.SingleBlock,
        TesseractVariables = new Dictionary<string, object>
        {
            ["tessedit_char_whitelist"] = "0123456789.$,",
            ["テキストードヘビーnr"] = false,
            ["アウトラインあたりのエッジの最大子数"] = 10
        }
    }
};

// Apply preprocessing filters for better accuracy
using OcrInput input = new OcrInput();
input.LoadPdf("financial-document.pdf");
input.Deskew();
input.EnhanceResolution(300);

OcrResult result = ocr.Read(input);

Imports IronOcr

' Example: Configure for financial documents
Dim ocr As New IronTesseract With {
    .Language = OcrLanguage.English,
    .Configuration = New TesseractConfiguration With {
        .PageSegmentationMode = TesseractPageSegmentationMode.SingleBlock,
        .TesseractVariables = New Dictionary(Of String, Object) From {
            {"tessedit_char_whitelist", "0123456789.$,"},
            {"テキストードヘビーnr", False},
            {"アウトラインあたりのエッジの最大子数", 10}
        }
    }
}

' Apply preprocessing filters for better accuracy
Using input As New OcrInput()
    input.LoadPdf("financial-document.pdf")
    input.Deskew()
    input.EnhanceResolution(300)

    Dim result As OcrResult = ocr.Read(input)
End Using