C#利用PaddleOCRSharp实现表格文字识别及可视化对比

using PaddleOCRSharp;
using OpenCvSharp;
using OpenCvSharp.Extensions;
using System.Drawing;
using System.IO;
using System.Windows.Forms;
using System; // 可能还需要其他基础命名空间

private PaddleOCREngine engine;

// 在窗体构造函数或需要时初始化
public Form1()
{
    InitializeComponent();
    OCRModelConfig config = null;
    OCRParameter param = new OCRParameter();
    engine = new PaddleOCREngine(config, param);
}

private void btnImageOCR_Click(object sender, EventArgs e)
{
    OpenFileDialog ofd = new OpenFileDialog();
    ofd.Filter = "图像文件|*.bmp;*.jpg;*.jpeg;*.png;*.tiff";
    if (ofd.ShowDialog() != DialogResult.OK) return;

    byte[] imageBytes = File.ReadAllBytes(ofd.FileName);
    Bitmap bitmap = new Bitmap(new MemoryStream(imageBytes));

    // 执行识别
    OCRResult result = engine.DetectText(bitmap);
    if (result != null)
    {
        textBox1.Text = result.Text; // 输出纯文本
    }
}

private void btnPDFOCR_Click(object sender, EventArgs e)
{
    OpenFileDialog ofd = new OpenFileDialog();
    ofd.Filter = "PDF文件|*.pdf";
    if (ofd.ShowDialog() != DialogResult.OK) return;

    byte[] pdfBytes = File.ReadAllBytes(ofd.FileName);
    
    // 设置回调显示处理进度
    Action<int> progress = page => Console.WriteLine($"正在处理第 {page} 页");
    var result = engine.DetectTextPDF(pdfBytes, 150, progress);

    StringBuilder sb = new StringBuilder();
    foreach (var page in result.Pages)
    {
        sb.AppendLine(page.Text);
    }
    textBox1.Text = sb.ToString();
}

private Bitmap DrawThreeImages(Bitmap original, OCRResult ocrResult)
{
    // 1. 将原图转为 Mat，确保为 3 通道彩色
    Mat originalMat = BitmapConverter.ToMat(original);
    if (originalMat.Channels() == 1)
        Cv2.CvtColor(originalMat, originalMat, ColorConversionCodes.GRAY2BGR);
    else if (originalMat.Channels() == 4)
        Cv2.CvtColor(originalMat, originalMat, ColorConversionCodes.BGRA2BGR);

    // 2. 第二张图：原图克隆，仅绘制框
    Mat boxesMat = originalMat.Clone();

    // 3. 第三张图：纯白色背景
    Mat textMat = new Mat(originalMat.Size(), originalMat.Type(), Scalar.White);

    // 定义颜色（BGR顺序）
    Scalar lightBlue = new Scalar(255, 255, 0); // 浅蓝色

    // 获取文本块列表（根据实际属性名调整，PaddleOCRSharp 中为 TextBlocks）
    var blocks = ocrResult.TextBlocks;
    if (blocks != null)
    {
        // 3.1 先用 OpenCV 绘制框到 boxesMat 和 textMat
        foreach (var block in blocks)
        {
            var points = block.BoxPoints; // 通常为 List<PointF> 或 PointF[]
            if (points == null || points.Count < 4) continue;

            Point[] pts = new Point[4];
            for (int i = 0; i < 4; i++)
                pts[i] = new Point((int)points[i].X, (int)points[i].Y);

            Cv2.Polylines(boxesMat, new[] { pts }, true, lightBlue, 2);
            Cv2.Polylines(textMat, new[] { pts }, true, lightBlue, 2);
        }

        // 3.2 将 textMat 转为 Bitmap，用 System.Drawing 绘制中文文字
        Bitmap textBmp = BitmapConverter.ToBitmap(textMat);
        textMat.Dispose();

        using (Graphics g = Graphics.FromImage(textBmp))
        {
            g.TextRenderingHint = System.Drawing.Text.TextRenderingHint.AntiAlias;

            foreach (var block in blocks)
            {
                var points = block.BoxPoints;
                if (points == null || points.Count < 4) continue;
                string text = block.Text;
                if (string.IsNullOrEmpty(text)) continue;

                // 计算文本框的边界矩形
                float minX = points.Min(p => p.X);
                float maxX = points.Max(p => p.X);
                float minY = points.Min(p => p.Y);
                float maxY = points.Max(p => p.Y);
                float width = maxX - minX;
                float height = maxY - minY;
                if (width <= 0 || height <= 0) continue;

                // 根据框高度动态设置字体大小（约0.4倍）
                float fontSize = height * 0.4f;
                fontSize = Math.Max(8, Math.Min(48, fontSize));

                using (Font font = new Font("Microsoft YaHei", fontSize, FontStyle.Regular, GraphicsUnit.Pixel))
                using (Brush brush = new SolidBrush(Color.Black))
                using (StringFormat sf = new StringFormat())
                {
                    sf.Alignment = StringAlignment.Center;
                    sf.LineAlignment = StringAlignment.Center;

                    float centerX = (minX + maxX) / 2;
                    float centerY = (minY + maxY) / 2;

                    g.DrawString(text, font, brush, centerX, centerY, sf);
                }
            }
        }

        // 将绘制好的 Bitmap 转回 Mat
        textMat = BitmapConverter.ToMat(textBmp);
        textBmp.Dispose();
    }

    // 4. 水平拼接三张图
    Mat[] mats = { originalMat, boxesMat, textMat };
    Mat resultMat = new Mat();
    Cv2.HConcat(mats, resultMat);

    // 5. 转换为 Bitmap
    Bitmap resultBitmap = BitmapConverter.ToBitmap(resultMat);

    // 6. 释放资源
    originalMat.Dispose();
    boxesMat.Dispose();
    textMat.Dispose();
    resultMat.Dispose();

    return resultBitmap;
}

private void btnImageOCR_Click(object sender, EventArgs e)
{
    // ... 前面的识别代码 ...
    if (ocrResult != null)
    {
        textBox1.Text = ocrResult.Text;

        // 生成三图对比
        Bitmap merged = DrawThreeImages(bitmap, ocrResult);

        // 显示新窗体
        Form2 form2 = new Form2();
        form2.pictureBox1.Image = merged;
        form2.Show();
    }
}