i. Order statistic filters are non-linear spatial filters whose response is based on the ordering(ranking) of the pixels contained in the image area encompassed by the filter, and then replacing the value in the center pixel with the value determined by the ranking result.

ii. The different types of order statistics filters include Median Filtering, Max and Min filtering and Mid-point filtering.

iii. Median Filtering : Replaces the value of a pixel by the median of the pixel values in the neighborhood of that pixel

iv. Max & Min Filtering : The max filtering is achieved using the following equation

f(x,y) = max g(s,t)

The min filtering is achieved using the following equation

f(x,y) = min g(s,t)

v. Mid-point filtering : Replaces the value of a pixel by the midpoint between the maximum and minimum pixels in a neighborhood

Advantages:

i. The advantages of median filtering are

• It works well for various noise types, with less blurring than linear filters of similar size

• Odd sized neighborhoods and efficient sorts yield a computationally efficient implementation

• Most commonly used order-statistic filter

ii. The advantages of Max and Min filtering are

• Max filters are Useful for finding the brightest points in an image

• They also tend to reduce pepper noise (i.e. dark pixel values

iii. The advantage of Mid-point filtering is

• Mid-Point filters are very useful for removing randomly distributed noise like Gaussian noise.