C#+OpenCV基础(十七)_计算图片相似度

合集 - C#+机器视觉OpenCV(27)

1.C#+OpenCV学习笔记(目录)-目录2024-07-102.C#+OpenCV基础(一)_加载创建复制保存图片2024-07-103.C#+OpenCV基础(二)_灰度化二值化2024-07-104.C#+OpenCV基础(三)_修改高宽剪切拼接缩放2024-07-105.C#+OpenCV基础(四)_旋转翻转透视2024-07-106.C#+OpenCV基础(五)_添加边框2024-07-107.C#+OpenCV基础(六)_均值中值高斯双边滤波2024-07-108.C#+OpenCV基础(七)_图像金字塔2024-07-109.C#+OpenCV基础(八)_获取修改图片亮度2024-07-1010.C#+OpenCV基础(九)_拆分合并图层2024-07-1011.C#+OpenCV基础(十)_灰度变化与直方图2024-07-1012.C#+OpenCV基础(十一)_图片基础计算2024-07-1013.C#+OpenCV基础(十二)_图片形态学计算2024-07-1014.C#+OpenCV基础(十三)_图片白平衡矫正2024-07-1015.C#+OpenCV基础(十四)_绘制像素、图形、文字2024-07-1016.C#+OpenCV基础(十五)_图像的基础分割方法2024-07-1117.C#+OpenCV基础(十六)_识别圆、直线、斑点、轮廓2024-07-11

18.C#+OpenCV基础(十七)_计算图片相似度2024-07-11

19.C#+OpenCV基础(十八)_模版匹配2024-07-1120.C#+OpenCV进阶(一)_人体识别2024-07-1121.C#+OpenCV进阶(二)_文字识别2024-07-1122.C#+OpenCV进阶(三)_操作摄像头与视频文件2024-07-1123.C#+OpenCV进阶(四)_录屏2024-07-1124.C#+OpenCV实战(一)_图片简易角度矫正2024-07-1125.C#+OpenCV实战(二)_春天转秋天2024-07-1126.C#+OpenCV实战(三)_玉米粒计数2024-07-1127.C#+OpenCV实战(四)_特定钢板缺陷检测2024-07-11

收起

1、SSIM算法计算相似度

/// <summary>
/// 两张图片的相似度(SSIM算法)
/// </summary>
/// <param name="mat1">图片1</param>
/// <param name="mat2">图片2</param>
/// <returns></returns>
public static Scalar CompareDetection_SSIM(Mat mat1, Mat mat2)
{
    // 将两个图片处理成同样大小，否则会有错误： The operation is neither 'array op array' (where arrays have the same size and the same number of channels), nor 'array op scalar', nor 'scalar op array'
    var image2 = new Mat();
    Cv2.Resize(mat2, image2, new OpenCvSharp.Size(mat1.Width, mat1.Height));

    double C1 = 6.5025, C2 = 58.5225;
    var validImage1 = new Mat();
    var validImage2 = new Mat();
    mat1.ConvertTo(validImage1, MatType.CV_32F); //数据类型转换为 float,防止后续计算出现错误
    image2.ConvertTo(validImage2, MatType.CV_32F);

    Mat image1_1 = validImage1.Mul(validImage1); //图像乘积
    Mat image2_2 = validImage2.Mul(validImage2);
    Mat image1_2 = validImage1.Mul(validImage2);

    Mat gausBlur1 = new Mat(), gausBlur2 = new Mat(), gausBlur12 = new Mat();
    Cv2.GaussianBlur(validImage1, gausBlur1, new OpenCvSharp.Size(11, 11), 1.5); //高斯卷积核计算图像均值
    Cv2.GaussianBlur(validImage2, gausBlur2, new OpenCvSharp.Size(11, 11), 1.5);
    Cv2.GaussianBlur(image1_2, gausBlur12, new OpenCvSharp.Size(11, 11), 1.5);

    //Mat imageAvgProduct = gausBlur1.Mul(gausBlur2);  // 均值乘积
    Mat u1Squre = gausBlur1.Mul(gausBlur1);          // 计算图1的均值的平方
    Mat u2Squre = gausBlur2.Mul(gausBlur2);          // 计算图2的均值的平方

    Mat squreAvg1 = new Mat(), squreAvg2 = new Mat();
    Cv2.GaussianBlur(image1_1, squreAvg1, new OpenCvSharp.Size(11, 11), 1.5);  // 图像1的平方的均值
    Cv2.GaussianBlur(image2_2, squreAvg2, new OpenCvSharp.Size(11, 11), 1.5);  // 图像2的平方的均值

    Mat imageConvariance = gausBlur12 - gausBlur1.Mul(gausBlur2);  // 计算协方差
    Mat imageVariance1 = squreAvg1 - gausBlur1.Mul(gausBlur1);     // 计算图1的方差
    Mat imageVariance2 = squreAvg2 - gausBlur2.Mul(gausBlur2);     // 计算图2的方差

    var member = ((2 * gausBlur1.Mul(gausBlur2) + C1).Mul(2 * imageConvariance + C2));
    var denominator = ((u1Squre + u2Squre + C1).Mul(imageVariance1 + imageVariance2 + C2));

    Mat ssim = new Mat();
    Cv2.Divide(member, denominator, ssim);

    var sclar = Cv2.Mean(ssim);

    return sclar;  // 变化率，即差异
}

2、颜色直方图计算相似度

  

/// <summary>
/// 两张图片的相似度(颜色直方图)
/// 图片相似度识别（精度不高，速度较快，可用于以图搜图）
/// </summary>
/// <param name="imgFile1"></param>
/// <param name="imgFile2"></param>
/// <returns></returns>
public static double Compare_Hist(Mat matA, Mat matB)
{
    // 拆分通道
    Cv2.Split(matA, out Mat[] matA_S);
    Cv2.Split(matB, out Mat[] matB_S);

    //直方图的像素范围   
    Rangef[] histRange = { new Rangef(0, 256) };

    //直方图数组大小
    int[] histSize = { 256 };

    //直方图输出数组
    Mat hist_A = new Mat();
    Mat hist_B = new Mat();

    bool uniform = true, accumulate = false;
    Cv2.CalcHist(matA_S, new int[] { 0, 1, 2 }, null, hist_A, 1, histSize, histRange, uniform, accumulate);
    Cv2.CalcHist(matB_S, new int[] { 0, 1, 2 }, null, hist_B, 1, histSize, histRange, uniform, accumulate);

    //归一化，排除图像分辨率不一致的影响
    Cv2.Normalize(hist_A, hist_A, 0, 1, NormTypes.MinMax, -1, null);
    Cv2.Normalize(hist_B, hist_B, 0, 1, NormTypes.MinMax, -1, null);

    //相关性比较
    var res = Cv2.CompareHist(hist_A, hist_B, HistCompMethods.Correl);
    return res;
}