Hello all, I have a small question concerning filtering operation. I have been looking throught the help of IDL as well as on the Internet but I can't find a function or solution to apply  a majority filter in IDL. In other words, I'm looking for a function that would be based on the same functioning principle as a smooth or median function but instead of giving the average or the meadian value to the central pixel of the boxcar, it would give the value of the most common value among the neighboring pixels. Does any of you know if such a function exist in IDL or have a solution to obtain the same result? Thank you for your help, Regards. Laure