module KMeans

open System.Collections.Generic
open System.Drawing

open Emgu.CV
open Emgu.CV.Structure

type Result = {
    fg: Image<Gray, byte>
    mean_bg: float
    mean_fg: float
    d_fg: Image<Gray, float32> } // Euclidean distances of the foreground to mean_fg.

let kmeans (img: Image<Gray, float32>) (fgFactor: float) : Result =
    let nbIteration = 3
    let w = img.Width
    let h = img.Height

    let min = ref [| 0.0 |]
    let minLocation = ref <| [| Point() |]
    let max = ref [| 0.0 |]
    let maxLocation = ref <| [| Point() |]
    img.MinMax(min, max, minLocation, maxLocation)

    let mutable mean_bg = (!max).[0] - ((!max).[0] - (!min).[0]) / 4.0
    let mutable mean_fg = (!min).[0] + ((!max).[0] - (!min).[0]) / 4.0
    use mutable d_bg = new Image<Gray, float32>(img.Size)
    let mutable d_fg = new Image<Gray, float32>(img.Size)
    let mutable fg = new Image<Gray, byte>(img.Size)

    for i in 1 .. nbIteration do
        d_bg <- img.AbsDiff(Gray(mean_bg))
        d_fg <- img.AbsDiff(Gray(mean_fg))

        CvInvoke.Compare(d_fg, d_bg, fg, CvEnum.CmpType.LessThan)

        let mutable bg_total = 0.0
        let mutable bg_nb = 0

        let mutable fg_total = 0.0
        let mutable fg_nb = 0

        for i in 0 .. h - 1 do
            for j in 0 .. w - 1 do
                if fg.Data.[i, j, 0] > 0uy
                then
                    fg_total <- fg_total + float img.Data.[i, j, 0]
                    fg_nb <- fg_nb + 1
                else
                    bg_total <- bg_total + float img.Data.[i, j, 0]
                    bg_nb <- bg_nb + 1

        mean_bg <- bg_total / float bg_nb
        mean_fg <- fg_total / float fg_nb

    { fg = fg; mean_bg = mean_bg; mean_fg = mean_fg; d_fg = d_fg }