使用 IronOCR 在 C# 中儲存可搜尋 PDF

處理多頁文檔

在處理多頁文件的PDF OCR 操作時，IronOCR 會依序處理每一頁，並維持原始文件結構。 以下是將多頁掃描版 PDF 檔案轉換為可搜尋 PDF 檔案的範例：

using IronOcr;

// Initialize IronTesseract with configuration
var ocrTesseract = new IronTesseract
{
    Configuration = 
    {
        RenderSearchablePdf = true,
        PageSegmentationMode = TesseractPageSegmentationMode.Auto
    }
};

// Load a multi-page PDF
using var pdfInput = new OcrPdfInput("multi-page-scan.pdf");

// Optionally specify page range (e.g., pages 1-10)
pdfInput.SelectPages(1, 10);

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

// Save as searchable PDF
result.SaveAsSearchablePdf("searchable-multi-page.pdf");

// Display total pages processed
Console.WriteLine($"Processed {result.Pages.Length} pages");

using IronOcr;

// Initialize IronTesseract with configuration
var ocrTesseract = new IronTesseract
{
    Configuration = 
    {
        RenderSearchablePdf = true,
        PageSegmentationMode = TesseractPageSegmentationMode.Auto
    }
};

// Load a multi-page PDF
using var pdfInput = new OcrPdfInput("multi-page-scan.pdf");

// Optionally specify page range (e.g., pages 1-10)
pdfInput.SelectPages(1, 10);

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

// Save as searchable PDF
result.SaveAsSearchablePdf("searchable-multi-page.pdf");

// Display total pages processed
Console.WriteLine($"Processed {result.Pages.Length} pages");

創建可搜尋的PDF時如何應用篩選器？

SaveAsSearchablePdf也接受一個布林標誌作為第二個參數，讓您可以對可搜尋的 PDF 套用篩選器或不套用篩選器，從而為開發人員提供選擇的靈活性。 使用影像最佳化濾鏡可以顯著提高 OCR 準確率，尤其是在處理低品質掃描件時。

下面是一個套用灰階濾鏡，然後透過在SaveAsSearchablePdf的第二個參數中設定true來儲存帶有濾鏡的 PDF 的範例。

:path=/static-assets/ocr/content-code-examples/how-to/image-quality-correction-searchable-pdf.cs

using IronOcr;

var ocr = new IronTesseract();
var ocrInput = new OcrInput();

// Load a PDF file
ocrInput.LoadPdf("invoice.pdf");

// Apply gray scale filter
ocrInput.ToGrayScale();
OcrResult result = ocr.Read(ocrInput);

// Save the result as a searchable PDF with filters applied
result.SaveAsSearchablePdf("outputGrayscale.pdf", true);

為了獲得最佳效果，建議使用篩選精靈自動確定適合您特定文件類型的最佳篩選器組合。 該工具會分析您的輸入並建議合適的預處理步驟。

性能考量

處理大量文件時，可考慮實施 多執行緒 OCR 操作以提高吞吐量。 IronOCR 支援並發處理，讓您同時處理多個文件：

using IronOcr;
using System.Threading.Tasks;
using System.Collections.Concurrent;

public class BatchPdfProcessor
{
    private readonly IronTesseract _ocr;

    public BatchPdfProcessor()
    {
        _ocr = new IronTesseract
        {
            Configuration = 
            {
                RenderSearchablePdf = true,
                // Configure for optimal performance
                Language = OcrLanguage.English
            }
        };
    }

    public async Task ProcessBatchAsync(string[] filePaths)
    {
        var results = new ConcurrentBag<(string source, string output)>();

        await Parallel.ForEachAsync(filePaths, async (filePath, ct) =>
        {
            using var input = new OcrImageInput(filePath);
            var result = _ocr.Read(input);

            string outputPath = Path.ChangeExtension(filePath, ".searchable.pdf");
            result.SaveAsSearchablePdf(outputPath);

            results.Add((filePath, outputPath));
        });

        Console.WriteLine($"Processed {results.Count} files");
    }
}

using IronOcr;
using System.Threading.Tasks;
using System.Collections.Concurrent;

public class BatchPdfProcessor
{
    private readonly IronTesseract _ocr;

    public BatchPdfProcessor()
    {
        _ocr = new IronTesseract
        {
            Configuration = 
            {
                RenderSearchablePdf = true,
                // Configure for optimal performance
                Language = OcrLanguage.English
            }
        };
    }

    public async Task ProcessBatchAsync(string[] filePaths)
    {
        var results = new ConcurrentBag<(string source, string output)>();

        await Parallel.ForEachAsync(filePaths, async (filePath, ct) =>
        {
            using var input = new OcrImageInput(filePath);
            var result = _ocr.Read(input);

            string outputPath = Path.ChangeExtension(filePath, ".searchable.pdf");
            result.SaveAsSearchablePdf(outputPath);

            results.Add((filePath, outputPath));
        });

        Console.WriteLine($"Processed {results.Count} files");
    }
}

進階配置選項

對於更高階的應用程式場景，您可以利用詳細的 Tesseract 配置來微調 OCR 引擎，以適應特定的文件類型或語言：

var advancedOcr = new IronTesseract
{
    Configuration = 
    {
        RenderSearchablePdf = true,
        TesseractVariables = new Dictionary<string, object>
        {
            { "preserve_interword_spaces", 1 },
            { "tessedit_char_whitelist", "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz" }
        },
        PageSegmentationMode = TesseractPageSegmentationMode.SingleColumn
    },
    Language = OcrLanguage.EnglishBest
};

var advancedOcr = new IronTesseract
{
    Configuration = 
    {
        RenderSearchablePdf = true,
        TesseractVariables = new Dictionary<string, object>
        {
            { "preserve_interword_spaces", 1 },
            { "tessedit_char_whitelist", "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz" }
        },
        PageSegmentationMode = TesseractPageSegmentationMode.SingleColumn
    },
    Language = OcrLanguage.EnglishBest
};