高斯拉普拉斯边缘检测算子(LOG)

图像边缘可表示为一阶过极点或二阶过零点.
拉普拉斯算子表示为d2f = a2f / a2x + a2f / a2y
由于噪声点对边缘检测影响较大,所以由高斯滤波和拉普拉斯算子结合,形成高斯拉普拉斯算子。
由高斯函数根据拉普拉斯算子的公式求导可得
高斯拉普拉斯边缘检测算子(LOG)_第1张图片
离散化,取sigma为1.0,则5x5模块为
{0.0175 0.0392 0.0431 0.0392 0.0175
0.0392 0 -0.0965 0 0.0392
0.0431 -0.0965 -0.3183 -0.0965 0.0431
0.0392 0 -0.0965 0 0.0392
0.0175 0.0392 0.0431 0.0392 0.0175}
对其取整,并使总和为0,则
{ -2, -4, -4, -4, -2,
-4, 0, 8, 0, -4,
-4, 8, 24, 8, -4,
-4, 0, 8, 0, -4,
-2, -4, -4, -4, -2 };

#include"cv.h"
#include "highgui.h"

void LOG(CvMat* gray, CvMat* edge);
int main()
{
    IplImage *src = cvLoadImage("flower.jpg",1);

    const int width = src->width;
    const int height = src->height;

    CvMat *gray = cvCreateMat(height, width, CV_8UC1);
    cvCvtColor(src, gray, CV_BGR2GRAY);

    CvMat *edge = cvCreateMat(height, width, CV_8UC1);
    LOG(gray, edge);



    cvShowImage("SRC", src);
    cvShowImage("GRAY", gray);
    cvShowImage("LOG", edge);
    cvWaitKey(0);

    cvCvtColor(gray, src, CV_GRAY2BGR);
    cvSaveImage("GRAY.bmp", src);

    cvCvtColor(edge, src, CV_GRAY2BGR);
    cvSaveImage("EDGE.bmp", src);

    cvReleaseMat(&gray);
    cvReleaseMat(&edge);
    return 0;
}
void LOG(CvMat* gray, CvMat* edge)
{
    const int width = gray->width;
    const int height = gray->height;

    cvZero(edge);

    CvMat* edgeTemp1 = cvCreateMat(height, width, CV_16SC1);

    cvZero(edgeTemp1);

    int Template1[25] =  { -2, -4, -4, -4, -2,
                          -4,  0,  8,  0, -4,
                          -4,  8,  24, 8, -4,
                          -4,  0,  8,  0, -4,
                          -2, -4, -4, -4, -2 };


    for (int j = 2; j < height - 2; j ++)
    {
        int* edgeTemp1Data = (int*)(edgeTemp1->data.ptr + j * edgeTemp1->step);
        uchar* edgeData = (uchar*)(edge->data.ptr + j * edge->step);
        for (int i = 2; i < width - 2; i ++)
        {
            for (int k = 0; k < 5; k ++)
            {
                for (int l = 0; l < 5; l ++)
                {
                    edgeTemp1Data[i] += Template1[5 * k + l] * ((uchar*)(gray->data.ptr + (j + k - 2) * gray->step))[i + l - 2];
                    if (abs(edgeTemp1Data[i]) > 255)
                    {
                        edgeData[i] = 255;
                    }
                    else
                    {
                        edgeData[i] = abs(edgeTemp1Data[i]);
                    }
                }
            }

        }
    }

    cvReleaseMat(&edgeTemp1);

}



源图,灰度图和效果图如下所示:
高斯拉普拉斯边缘检测算子(LOG)_第2张图片

你可能感兴趣的:(边缘检测)