sorry i haven't found a good title for these three questions i'm wondering if someone could give me explaination with proof (if possible ) of these three questions :
- Given a grey-level image stored as a rectangular array of grey-level values, describe what the mean and median filters with an n x n kernel (neighborhood) do to the grey-levels of the image?
- Describe the visual effect on an image of the mean and median filters. What happens when the size n of the neighborhood increases ?
- Explain what are Gaussian noise and salt-and-pepper noise. Which type of filter is suitable for removing each type of noise ?
For each pixel in the original image, a 2n-1 x 2n-1 convolution matrix is centered on it and multiplied with the surrounding greyscale values, element-wise.
Mean and median filters result in an image blur, with the amount of blur increasing as n is increased.
Gaussian noise follows a normal distribution (the probability of a pixel changing by a certain value follows this distribution). Salt and pepper noise sometimes occurs from pixels being randomly set to near either their maximum (salt) or minimum (pepper) values. A mean filter might be more appropriate for gaussian noise, whereas a median filter helps ignore significant outliers (salt and pepper).