Howto:使用C#在OCR之前提高PDF质量

using PdfSharp;
using PdfSharp.Pdf;
using PdfSharp.Drawing;
using System.IO;

public static void ImprovePdfQuality(string inputFile, string outputFile)
{
    // 打开PDF文件
    PdfDocument document = PdfReader.Open(inputFile);

    // 设置输出文件
    PdfDocument outputDocument = new PdfDocument();
    outputDocument.Options.CompressContent = true;
    outputDocument.Options.ColorMode = PdfColorMode.Rgb;
    outputDocument.Options.FlateEncodeMode = PdfFlateEncodeMode.BestCompression;

    // 遍历每一页
    foreach (PdfPage page in document.Pages)
    {
        // 创建一个新的页面
        PdfPage outputPage = outputDocument.AddPage();
        outputPage.Width = page.Width;
        outputPage.Height = page.Height;

        // 绘制原始页面内容
        XGraphics graphics = XGraphics.FromPdfPage(outputPage);
        graphics.DrawImage(XImage.FromFile(inputFile, page.PageNumber - 1), 0, 0, outputPage.Width, outputPage.Height);

        // 保存新页面
        outputDocument.Save(outputFile);
    }

    // 关闭文件
    document.Close();
    outputDocument.Close();
}

Install-Package PdfSharp