OpenCV重写冈萨雷斯——添加高斯噪声

高斯噪声的概率分布

代码中添加噪声用到了Box-Muller变换原理 具体原理就不列出来了

更详细求解公式的可以转https://blog.csdn.net/weixin_41793877/article/details/84700875

---

//给图像加入高斯噪声
#include <cmath>
#include <limits>
#include <cstdlib>
#include <iostream>
#include <opencv2\opencv.hpp>


using namespace cv;
using namespace std;

double generateGaussianNoise(double m, double sigma);
Mat addGaussianNoise(Mat &srcImag);
Mat CalcHist(Mat src);
string st = "E:\\冈萨雷斯OpenCV重写\\DIP3E_CH05_Original_Images\\DIP3E_CH05_Original_Images\\";


//添加高斯噪声
int main()
{
	Mat srcImage = imread(st + "Fig0503 (original_pattern).tif",0);
	Mat histsrc = CalcHist(srcImage);
	imshow("Hist1", histsrc);
	imshow("原图像", srcImage);
	Mat dstImage = addGaussianNoise(srcImage);
	Mat histdst = CalcHist(dstImage);
	imshow("HistD", histdst);
	imshow("加入高斯噪声后的图像", dstImage);

	Mat testimg(512, 512, CV_8UC1, Scalar(0));
	testimg = addGaussianNoise(testimg);
	Mat histtest = CalcHist(testimg);
	imshow("histtest", histtest);
	imshow("高斯噪声图像", testimg);


	waitKey();
	return 0;
}

//生成高斯噪声
double generateGaussianNoise(double mu, double sigma)
{
	//定义小值
	const double epsilon = numeric_limits<double>::min();
	static double z0, z1;
	static bool flag = false;
	flag = !flag;
	//flag为假 构造高斯随机变量X
	if (!flag)
		return z1 * sigma + mu;
	double u1, u2;
	//构造随机变量(均匀分布)
	do
	{
		u1 = rand() * (1.0 / RAND_MAX);
		u2 = rand() * (1.0 / RAND_MAX);
	} while (u1 <= epsilon);
	//flag为真 构造高斯随机变量
	z0 = sqrt(-2.0*log(u1))*cos(2 * CV_PI*u2);
	z1 = sqrt(-2.0*log(u1))*sin(2 * CV_PI*u2);
	return z0*sigma + mu;
}

//为图像加入高斯噪声
Mat addGaussianNoise(Mat &srcImag)
{
	Mat dstImage = srcImag.clone();
	int channels = dstImage.channels();
	int rowsNumber = dstImage.rows;
	int colsNumber = dstImage.cols*channels;
	//推断图像的连续性
	//意思 查看储存类型 是矩阵还是行向量 内存足够大的情况下 会以行向量的方式保存
	if (dstImage.isContinuous())
	{
		colsNumber *= rowsNumber;
		rowsNumber = 1;
	}
	for (int i = 0; i < rowsNumber; i++)
	{
		for (int j = 0; j < colsNumber; j++)
		{
			//加入高斯噪声
			int val = dstImage.ptr<uchar>(i)[j] +
				generateGaussianNoise(10,10);
			if (val < 0)
				val = 0;
			if (val>255)
				val = 255;
			dstImage.ptr<uchar>(i)[j] = (uchar)val;
		}
	}
	return dstImage;
}

//计算直方图
Mat CalcHist(Mat src)
{
	const int channels[] = { 0 };
	const int histsize[] = { 255 };
	float range[] = { 0, 256 };
	const float* ranges[] = { range };
	Mat hist;
	calcHist(&src,1 ,channels, Mat(), hist,1, histsize, ranges);
	
	normalize(hist, hist, 0, 255, NORM_MINMAX);

	Mat  maphist1 = Mat::zeros(Size(256, 256), CV_8UC1);
	for (int i = 1; i < 255; i++)
	{
		line(maphist1, Point(i - 1, 255 - hist.at<float>(i - 1)), Point(i, 255 - hist.at<float>(i)), Scalar(255));
	}
	
	return maphist1;
}