图像的二阶导数
![在这里插入图片描述](https://img-blog.csdnimg.cn/direct/9bd627e3d12949c2af29cadb30d9fdfe.png)
![在这里插入图片描述](https://img-blog.csdnimg.cn/direct/d248bbee79a64105a0e9cfc236e1875a.png)
在二阶导数的时候,最大变化处的值为零即边缘是零值。通过二阶
导数计算,依据此理论我们可以计算图像二阶导数,提取边缘。
Laplance算子
![在这里插入图片描述](https://img-blog.csdnimg.cn/direct/018fcc4840944d959336063fcc0b047d.png)
void Laplacian( InputArray src, OutputArray dst, int ddepth,int ksize = 1, double scale = 1, double delta = 0,int borderType = BORDER_DEFAULT );
代码示例
#include <opencv2/opencv.hpp>
#include <iostream>
using namespace cv;
int main(int argc, char** argv) {
Mat src, dst;
src = imread("D:/vcprojects/images/lena.png");
if (!src.data) {
printf("could not load image");
}
char input_title[] = "input image";
char output_title[] = "Laplaiance Result";
namedWindow(input_title);
imshow(input_title, src);
Mat gray_src, edge_image;
GaussianBlur(src, dst, Size(3, 3), 0, 0);
cvtColor(dst, gray_src, COLOR_BGR2GRAY);
Laplacian(gray_src, edge_image, CV_16S, 3);
convertScaleAbs(edge_image, edge_image);
threshold(edge_image, edge_image, 0, 255, THRESH_OTSU | THRESH_BINARY);
namedWindow(output_title, CV_WINDOW_AUTOSIZE);
imshow(output_title, edge_image);
waitKey(0);
return 0;
}