การตรวจสอบคําหลักภาพอัตโนมัติด้วย Aspose.OCR & .NET

dotnet new console -n ImageArchiveKeywordAudit -f net8.0
cd ImageArchiveKeywordAudit
dotnet add package Aspose.OCR

// Exact shape used in the gist
List<string> keywords = new List<string>
{
    "mountains", "beaches", "forests", "landscape"
};

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

namespace ImageArchiveKeywordAudit
{
    class Program
    {
        static void Main(string[] args)
        {
            // Path to the image archive directory (edit to your folder)
            string imageDirectory = @"C:\Path\To\ImageArchive";

            // Keyword list for auditing (matches the gist approach)
            List<string> keywords = new List<string>
            {
                "mountains", "beaches", "forests", "landscape"
            };

            // Initialize Aspose.OCR API (license is optional)
            // new License().SetLicense("Aspose.Total.lic");
            using (AsposeOcr api = new AsposeOcr())
            {
                // Process each JPG in the directory (same filter style as the gist)
                foreach (string imagePath in Directory.GetFiles(imageDirectory, "*.jpg"))
                {
                    // Extract text from the image
                    string extractedText = api.RecognizeImageFile(imagePath);

                    // Audit the extracted text against the keyword list
                    bool containsKeywords = AuditText(extractedText, keywords);

                    // Output the results
                    Console.WriteLine($"Image: {imagePath} - Contains Keywords: {containsKeywords}");
                }
            }
        }

        // Method to audit extracted text against a list of keywords (as in gist)
        static bool AuditText(string text, List<string> keywords)
        {
            foreach (string keyword in keywords)
            {
                if (text.Contains(keyword, StringComparison.OrdinalIgnoreCase))
                {
                    return true;
                }
            }
            return false;
        }
    }
}

// Replace the single GetFiles with this multi-pattern approach
string[] patterns = new[] { "*.jpg", "*.jpeg", "*.png", "*.tif", "*.tiff", "*.bmp" };
var imageFiles = new List<string>();
foreach (var pattern in patterns)
    imageFiles.AddRange(Directory.GetFiles(imageDirectory, pattern, SearchOption.TopDirectoryOnly));

// After OCR:
var matched = new List<string>();
var missing = new List<string>();

foreach (var k in keywords)
    (extractedText.IndexOf(k, StringComparison.OrdinalIgnoreCase) >= 0 ? matched : missing).Add(k);

Console.WriteLine($"Image: {Path.GetFileName(imagePath)} | Matched: [{string.Join(", ", matched)}] | Missing: [{string.Join(", ", missing)}]");

string reportPath = Path.Combine(imageDirectory, "audit-report.csv");
bool writeHeader = !File.Exists(reportPath);

using (var sw = new StreamWriter(reportPath, append: true))
{
    if (writeHeader)
        sw.WriteLine("Image,ContainsKeywords,Matched,Missing");

    sw.WriteLine($"\"{Path.GetFileName(imagePath)}\",{matched.Count > 0},\"{string.Join(";", matched)}\",\"{string.Join(";", missing)}\"");
}

# Adjust paths as needed
$solutionRoot = "C:\Path\To\ImageArchiveKeywordAudit"
$imageDir     = "C:\Path\To\ImageArchive"

# Build and run
dotnet build "$solutionRoot" -c Release
& "$solutionRoot\bin\Release\net8.0\ImageArchiveKeywordAudit.exe"

schtasks /Create /TN "ImageKeywordAudit" /TR "\"C:\Path\To\ImageArchiveKeywordAudit\bin\Release\net8.0\ImageArchiveKeywordAudit.exe\"" /SC DAILY /ST 02:00