Question

As we all know, Gaussian Noise follows Gaussian or Normal distribution, and that distribution follows a $BELL$ $CURVE$.

enter image description here

As we can see that most of the values are centered around the mean.

Now consider this image

enter image description here

When I add Gaussian noise to this image I get something like this

enter image description here

As we can see that the noise appears to be $UNIFORMLY$ $DISTRIBUTED$ throughout the image. There is no region where we can say that the noises concentrated around the mean value

So how can these be called Gaussian Noise?

The Code that I have used in octave is given below

 pkg load image;

I=imread('C:\Users\Hirak\Desktop\apple.jpg');
I=rgb2gray(I);

J = imnoise(I,'gaussian',0.02);
K = medfilt2(J);
imshow(J);
Was it helpful?

Solution

The noise is Gaussian noise because the values you add to your existing images follow a Gaussian distribution, not the locations of where you add the noise - that is uniform (and not random at all - each pixel gets Gaussian noise added to it).

Licensed under: CC-BY-SA with attribution
Not affiliated with cs.stackexchange
scroll top