設定と言語

IronTesseract ocr = new IronTesseract
{
    Configuration = new TesseractConfiguration
    {
        ReadBarCodes = false,
        RenderHocr = true,
        TesseractVariables = null,
        WhiteListCharacters = null,
        BlackListCharacters = "`ë|^",
    },
    MultiThreaded = false,
    Language = OcrLanguage.English,
    EnableTesseractConsoleMessages = true, // False as default
};

using IronOcr;

IronTesseract ocr = new IronTesseract
{
    Configuration = new TesseractConfiguration
    {
        // Whitelist alphanumeric characters and common punctuation
        WhiteListCharacters = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789.,-?!$() /",
        // Blacklist uncommon characters 
        BlackListCharacters = "`ë|^",
    },

    // Languages available for advanced reading are English, Japanese, Korean, LatinAlphabet   
    Language = OcrLanguage.English
};

using IronOcr;

var ocr = new IronTesseract();

// Set the OCR to use Chinese Simplified
ocr.Language = OcrLanguage.ChineseSimplified;
using (var input = new OcrInput())
{
    var result = ocr.Read(input);

    // Store the recognized text in a string
    string testResult = result.Text;
}

using IronOcr;

// Instantiate IronTesseract
IronTesseract ocrTesseract = new IronTesseract()
{   // Set primary language to English
    Language = OcrLanguage.EnglishBest,
};

// Set secondary language to Russian
ocrTesseract.AddSecondaryLanguage(OcrLanguage.Russian);

// Add PDF
using var pdfInput = new OcrPdfInput(@"example.pdf");

// Perform OCR
OcrResult result = ocrTesseract.Read(pdfInput);

// Output extracted text to console
Console.WriteLine(result.Text);

using IronOcr;

var ocrTesseract = new IronTesseract();
ocrTesseract.UseCustomTesseractLanguageFile("custom_tesseract_files/custom.traineddata");
using var ocrInput = new OcrInput();
ocrInput.LoadImage(@"sample.png");
var ocrResult = ocrTesseract.Read(ocrInput);
Console.WriteLine(ocrResult.Text);