Cases of OpenCV image enhancement

Opencv Implementation of image enhancement algorithm ( Histogram equalization 、Laplace、Log、Gamma) | Chuan·Yen

One 、 brief introduction

Image enhancement algorithm is a process of image distortion , To highlight some of the characteristics of the response , It is convenient for us to process the region of interest , There are generally four ways Histogram equalization 、Laplace、Log、Gamma

Two 、 Histogram equalization

The methods of image contrast enhancement can be divided into two categories : One is Direct contrast enhancement method ; The other is Indirect contrast enhancement method .
Histogram stretching and Histogram equalization Two of the most common indirect contrast enhancement methods .

Histogram stretching It is to adjust the histogram through contrast stretching , thus “ expand ” The difference between foreground and background gray , To enhance contrast , This method can be realized by linear or nonlinear methods .
Histogram equalization Then, the gray value is calculated by using the accumulation function “ adjustment ” To achieve contrast enhancement .

• advantage : This method is very useful for both background and foreground images that are too bright or too dark , This method, in particular, can bring about X Better display of bone structure in light images and better details in overexposed or underexposed photos . One of the main advantages of this method is that it is a fairly intuitive technology and reversible operation , If the equalization function is known , Then we can restore the original histogram , And the amount of calculation is not big .
• shortcoming : The disadvantage is that it doesn't choose to process the data , It may increase the contrast of background noise and reduce the contrast of useful signals ; The gray level of the transformed image is reduced , Some details disappear ; Some images , If the histogram has a peak , After treatment, the contrast is unnaturally enhanced .
  Realization of color image histogram equalization ：
• 

#if 1 //  Image enhancement algorithm  -- Histogram equalization image enhancement 
int main(int args, char* arg)
{
	Mat	src = imread("C:\\Users\\19473\\Desktop\\opencv_images\\88.jpg");
	if (!src.data)
	{
		printf("could not  load  image....\n");
	}
	imshow("input_demo", src);

	Mat stc_bgr[3];
	Mat  dst;//  Enhanced image 
	split(src, stc_bgr); // 
	for (int i=0;i<3;i++) 
	{
		equalizeHist(stc_bgr[i], stc_bgr[i]);
	}
	merge(stc_bgr,3,dst); //  Merge 
	imshow(" Enhanced image ", dst);
	waitKey(0);
	return -1;
}
#endif

3、 ... and 、Laplace Image enhancement

Laplace operator can enhance the local image contrast .
Laplace 8 Neighborhood convolution kernel :
0  -1  0
-1  5  -1
0   -1  0
use filter2D Function to convolute the image :

#if 1 //  Image enhancement algorithm  -- Laplace uses convolution kernel to enhance 
int main(int args, char* arg)
{
	Mat	src = imread("C:\\Users\\19473\\Desktop\\opencv_images\\88.jpg");
	if (!src.data)
	{
		printf("could not  load  image....\n");
	}
	imshow("input_demo", src);
    Mat dst;
	Mat kernel = (Mat_<int>(3, 3) << 0, -1, 0, -1, 5, -1, 0, -1, 0);
	filter2D(src, dst, src.depth(), kernel);

	
	imshow(" Enhanced image ", dst);
	waitKey(0);
	return -1;
}
#endif

Four 、 logarithm Log Transform image enhancement

Logarithmic transformation can expand the low gray value part of the image , Show more details in the low gray part , Compress its high gray value part , Reduce the details of high gray value parts , So as to emphasize the low gray part of the image . Change the way ：

  For different bases , The larger the base , The lower the gray scale, the stronger the gray scale , The stronger the compression of the high gray part .

 

#if 1 //  Image enhancement algorithm  --log  Transform enhancement 
int main(int args, char* arg)
{
	Mat	src = imread("C:\\Users\\19473\\Desktop\\opencv_images\\613.png");
	if (!src.data)
	{
		printf("could not  load  image....\n");
	}
	imshow(" Original image ", src);
	//  Be careful  ： CV_32FC3
	Mat dst(src.size(), CV_32FC3);

	for (int i = 0; i < src.rows; i++)
	{
		for (int j = 0; j < src.cols; j++)
		{
			//  Yes bgr  Each channel of is calculated 
			dst.at<Vec3f>(i, j)[0] = log(1 + src.at<Vec3b>(i, j)[0]);
		    dst.at<Vec3f>(i, j)[1] = log(1 + src.at<Vec3b>(i, j)[1]);
			dst.at<Vec3f>(i, j)[2] = log(1 + src.at<Vec3b>(i, j)[2]);
		}
	}
	//  normalization 
	normalize(dst, dst, 0, 255, CV_MINMAX);

	convertScaleAbs(dst, dst);

	imshow(" Enhanced image ", dst);
	waitKey(0);
	return -1;
}
#endif

5、 ... and 、  Image enhancement of gamma transform

Gamma transform is mainly used for image correction , Correct the image with too high or too low gray level , Enhance contrast . The transformation formula is to multiply each pixel value on the original image ：

Gamma transform is low for image contrast , And the overall brightness value is high （ For camera overexposure ） In this case, the image enhancement effect is obvious .

#if 1 //  Image enhancement algorithm  --gamma
int  Gamma = 2;
int main(int args, char* arg)
{
	Mat	src = imread("C:\\Users\\19473\\Desktop\\opencv_images\\88.jpg");
	if (!src.data)
	{
		printf("could not  load  image....\n");
	}
	imshow(" Original image ", src);
	//  Be careful  ： CV_32FC3
	Mat dst(src.size(), CV_32FC3);

	for (int i = 0; i < src.rows; i++)
	{
		for (int j = 0; j < src.cols; j++)
		{
			//  Yes bgr  Each channel of is calculated 
			dst.at<Vec3f>(i, j)[0] = pow(src.at<Vec3b>(i, j)[0], Gamma);
			dst.at<Vec3f>(i, j)[1] = pow(src.at<Vec3b>(i, j)[1], Gamma);
			dst.at<Vec3f>(i, j)[2] = pow(src.at<Vec3b>(i, j)[2], Gamma);
		}
	}
	//  normalization 
	normalize(dst, dst, 0, 255, CV_MINMAX);

	convertScaleAbs(dst, dst);

	imshow(" Enhanced image ", dst);
	waitKey(0);
	return -1;
}
#endif