median.jl

function median_filter{T, N}(img::AbstractArray{T, N}, window::NTuple{N, Int})

    all(isodd(w) for w in window) || error("entries in window must be odd, got $window")

    R = CartesianRange(size(img))
    half_window = map(w->w>>1, window)
    Rinner = CartesianRange(first(R)+CartesianIndex(half_window), last(R)-CartesianIndex(half_window))

    for i in Rinner
        if i[1] = first(Rinner)[1]
            #reinitialize histogram
        end
        #update elements and calculate new median
    end
end