IronOCRでC#の文字認識・テキスト抽出結果の信頼度スコアを活用する方法

using IronOcr;

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

// Add image
using var imageInput = new OcrImageInput("sample.tiff");
// Perform OCR
OcrResult ocrResult = ocrTesseract.Read(imageInput);

// Get confidence level
double confidence = ocrResult.Confidence;

Imports IronOcr

' Instantiate IronTesseract
Private ocrTesseract As New IronTesseract()

' Add image
Private imageInput = New OcrImageInput("sample.tiff")
' Perform OCR
Private ocrResult As OcrResult = ocrTesseract.Read(imageInput)

' Get confidence level
Private confidence As Double = ocrResult.Confidence

// Get page confidence level
double pageConfidence = ocrResult.Pages[0].Confidence;

// Get paragraph confidence level
double paragraphConfidence = ocrResult.Paragraphs[0].Confidence;

// Get line confidence level
double lineConfidence = ocrResult.Lines[0].Confidence;

// Get word confidence level
double wordConfidence = ocrResult.Words[0].Confidence;

// Get character confidence level
double characterConfidence = ocrResult.Characters[0].Confidence;

// Get block confidence level
double blockConfidence = ocrResult.Blocks[0].Confidence;

' Get page confidence level
Dim pageConfidence As Double = ocrResult.Pages(0).Confidence

' Get paragraph confidence level
Dim paragraphConfidence As Double = ocrResult.Paragraphs(0).Confidence

' Get line confidence level
Dim lineConfidence As Double = ocrResult.Lines(0).Confidence

' Get word confidence level
Dim wordConfidence As Double = ocrResult.Words(0).Confidence

' Get character confidence level
Dim characterConfidence As Double = ocrResult.Characters(0).Confidence

' Get block confidence level
Dim blockConfidence As Double = ocrResult.Blocks(0).Confidence

using IronOcr;
using static IronOcr.OcrResult;

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

// Add image
using var imageInput = new OcrImageInput("Potter.tiff");
// Perform OCR
OcrResult ocrResult = ocrTesseract.Read(imageInput);

// Get choices
Choice[] choices = ocrResult.Characters[0].Choices;

Imports IronOcr
Imports IronOcr.OcrResult

' Instantiate IronTesseract
Private ocrTesseract As New IronTesseract()

' Add image
Private imageInput = New OcrImageInput("Potter.tiff")
' Perform OCR
Private ocrResult As OcrResult = ocrTesseract.Read(imageInput)

' Get choices
Private choices() As Choice = ocrResult.Characters(0).Choices

using IronOcr;

public class DocumentValidator
{
    private readonly IronTesseract ocr = new IronTesseract();

    public bool ValidatePassportNumber(string imagePath, double minConfidence = 95.0)
    {
        using var input = new OcrImageInput(imagePath);

        // Configure for passport reading
        ocr.Configuration.ReadBarCodes = true;
        ocr.Configuration.PageSegmentationMode = TesseractPageSegmentationMode.SingleLine;

        // Apply preprocessing
        input.Deskew();
        input.Scale(200); // Upscale for better accuracy

        var result = ocr.Read(input);

        // Find passport number pattern
        var passportLine = result.Lines
            .Where(line => line.Text.Contains("P<") || IsPassportNumberFormat(line.Text))
            .FirstOrDefault();

        if (passportLine != null)
        {
            Console.WriteLine($"Passport line found: {passportLine.Text}");
            Console.WriteLine($"Confidence: {passportLine.Confidence:F2}%");

            // Only accept if confidence meets threshold
            return passportLine.Confidence >= minConfidence;
        }

        return false;
    }

    private bool IsPassportNumberFormat(string text)
    {
        // Simple passport number validation
        return System.Text.RegularExpressions.Regex.IsMatch(text, @"^[A-Z]\d{7,9}$");
    }
}

Imports IronOcr

Public Class DocumentValidator
    Private ReadOnly ocr As New IronTesseract()

    Public Function ValidatePassportNumber(imagePath As String, Optional minConfidence As Double = 95.0) As Boolean
        Using input As New OcrImageInput(imagePath)

            ' Configure for passport reading
            ocr.Configuration.ReadBarCodes = True
            ocr.Configuration.PageSegmentationMode = TesseractPageSegmentationMode.SingleLine

            ' Apply preprocessing
            input.Deskew()
            input.Scale(200) ' Upscale for better accuracy

            Dim result = ocr.Read(input)

            ' Find passport number pattern
            Dim passportLine = result.Lines _
                .Where(Function(line) line.Text.Contains("P<") OrElse IsPassportNumberFormat(line.Text)) _
                .FirstOrDefault()

            If passportLine IsNot Nothing Then
                Console.WriteLine($"Passport line found: {passportLine.Text}")
                Console.WriteLine($"Confidence: {passportLine.Confidence:F2}%")

                ' Only accept if confidence meets threshold
                Return passportLine.Confidence >= minConfidence
            End If

            Return False
        End Using
    End Function

    Private Function IsPassportNumberFormat(text As String) As Boolean
        ' Simple passport number validation
        Return System.Text.RegularExpressions.Regex.IsMatch(text, "^[A-Z]\d{7,9}$")
    End Function
End Class

using IronOcr;

// Create an optimized OCR workflow
IronTesseract ocr = new IronTesseract();

using var input = new OcrImageInput("low_quality_scan.jpg");

// Apply multiple filters to improve confidence
input.Deskew();           // Correct rotation
input.DeNoise();          // Remove noise
input.Sharpen();          // Enhance edges
input.Dilate();           // Thicken text
input.Scale(150);         // Upscale for clarity

// Configure for accuracy over speed
ocr.Configuration.TesseractVersion = TesseractVersion.Tesseract5;
ocr.Configuration.EngineMode = TesseractEngineMode.TesseractOnly;

var result = ocr.Read(input);

Console.WriteLine($"Document confidence: {result.Confidence:F2}%");

// Generate confidence report
var confidenceReport = result.Pages
    .Select((page, index) => new
    {
        PageNumber = index + 1,
        Confidence = page.Confidence,
        WordCount = page.Words.Length,
        LowConfidenceWords = page.Words.Count(w => w.Confidence < 80)
    });

foreach (var page in confidenceReport)
{
    Console.WriteLine($"Page {page.PageNumber}: {page.Confidence:F2}% confidence");
    Console.WriteLine($"  Total words: {page.WordCount}");
    Console.WriteLine($"  Low confidence words: {page.LowConfidenceWords}");
}

Imports IronOcr

' Create an optimized OCR workflow
Dim ocr As New IronTesseract()

Using input As New OcrImageInput("low_quality_scan.jpg")

    ' Apply multiple filters to improve confidence
    input.Deskew()           ' Correct rotation
    input.DeNoise()          ' Remove noise
    input.Sharpen()          ' Enhance edges
    input.Dilate()           ' Thicken text
    input.Scale(150)         ' Upscale for clarity

    ' Configure for accuracy over speed
    ocr.Configuration.TesseractVersion = TesseractVersion.Tesseract5
    ocr.Configuration.EngineMode = TesseractEngineMode.TesseractOnly

    Dim result = ocr.Read(input)

    Console.WriteLine($"Document confidence: {result.Confidence:F2}%")

    ' Generate confidence report
    Dim confidenceReport = result.Pages _
        .Select(Function(page, index) New With {
            .PageNumber = index + 1,
            .Confidence = page.Confidence,
            .WordCount = page.Words.Length,
            .LowConfidenceWords = page.Words.Count(Function(w) w.Confidence < 80)
        })

    For Each page In confidenceReport
        Console.WriteLine($"Page {page.PageNumber}: {page.Confidence:F2}% confidence")
        Console.WriteLine($"  Total words: {page.WordCount}")
        Console.WriteLine($"  Low confidence words: {page.LowConfidenceWords}")
    Next
End Using