画像におけるテキスト類似性とプラジアリズムを検出する方法

string[] archiveFiles = Directory.GetFiles("./archive", "*.png");
string[] submissionFiles = Directory.GetFiles("./submissions", "*.png");

RecognitionSettings settings = new RecognitionSettings();
settings.Language = Language.English;
AsposeOcr ocr = new AsposeOcr();
Dictionary<string, string> archiveTexts = new Dictionary<string, string>();
foreach (string file in archiveFiles)
{
    string text = ocr.Recognize(new OcrInput(InputType.SingleImage) { file }, settings)[0].RecognitionText;
    archiveTexts[file] = text;
}

foreach (string subFile in submissionFiles)
{
    string subText = ocr.Recognize(new OcrInput(InputType.SingleImage) { subFile }, settings)[0].RecognitionText;
    foreach (var kvp in archiveTexts)
    {
        double similarity = JaccardSimilarity(subText, kvp.Value); // custom function or library
        if (similarity > 0.8) // Tune threshold for your needs
        {
            File.AppendAllText("plagiarism_log.csv", $"{subFile},{kvp.Key},{similarity}\n");
        }
    }
}

// Example Jaccard similarity (token-based)
double JaccardSimilarity(string text1, string text2)
{
    var set1 = new HashSet<string>(text1.Split());
    var set2 = new HashSet<string>(text2.Split());
    int intersect = set1.Intersect(set2).Count();
    int union = set1.Union(set2).Count();
    return (double)intersect / union;
}

using Aspose.OCR;
using System;
using System.Collections.Generic;
using System.IO;

class Program
{
    static void Main(string[] args)
    {
        string[] archiveFiles = Directory.GetFiles("./archive", "*.png");
        string[] submissionFiles = Directory.GetFiles("./submissions", "*.png");
        RecognitionSettings settings = new RecognitionSettings();
        settings.Language = Language.English;
        AsposeOcr ocr = new AsposeOcr();
        Dictionary<string, string> archiveTexts = new Dictionary<string, string>();
        foreach (string file in archiveFiles)
            archiveTexts[file] = ocr.Recognize(new OcrInput(InputType.SingleImage) { file }, settings)[0].RecognitionText;
        foreach (string subFile in submissionFiles)
        {
            string subText = ocr.Recognize(new OcrInput(InputType.SingleImage) { subFile }, settings)[0].RecognitionText;
            foreach (var kvp in archiveTexts)
            {
                double sim = JaccardSimilarity(subText, kvp.Value);
                if (sim > 0.8)
                    File.AppendAllText("plagiarism_log.csv", $"{subFile},{kvp.Key},{sim}\n");
            }
        }
    }
    static double JaccardSimilarity(string text1, string text2)
    {
        var set1 = new HashSet<string>(text1.Split());
        var set2 = new HashSet<string>(text2.Split());
        int intersect = set1.Intersect(set2).Count();
        int union = set1.Union(set2).Count();
        return (double)intersect / union;
    }
}