* 這個例子檢查瓶口缺陷，
* 首先找到瓶口，找瓶口的方法就通過自動閾值，然後進行圓擬合
*邊緣檢測，找到邊緣之後縮小圓，找到瓶口這一個圓帶狀影象
*把圓帶拉抻變換成長方形，這樣其實是為了使用平均值濾波，把視窗的設定為【500，3】大小，這樣就可以把垂直方向的差異提取出來
*然後再通過dyn_threshold找出差異位置，計算連通域，然後再找出連通域高度大於9的，如果有，就認為包含缺陷，如果沒有就不包含缺陷
*然後給定一個動態的閾值來檢測缺陷，最後顯示缺陷
*總結，這個例子主要是看瓶口徑向一致性的檢查，正常的瓶口徑向一致性很好，但是有破損的則不然，所以這是一個很好的思路
* tuning parameters
*均值濾波視窗寬度
SmoothX := 501
*動態閾值操作的容差值，但是下面直接使用的55這個值，沒使用變數
ThresholdOffset := 55
*找到的瑕疵高度最小值
MinDefectSize := 9
* 
* initialization
PolarResolution := 640
RingSize := 70
get_system ('store_empty_region', StoreEmptyRegion)
set_system ('store_empty_region', 'false')
read_image (Image, 'bottles/bottle_mouth_01')
dev_update_off ()
dev_close_window ()
dev_close_window ()
dev_open_window_fit_image (Image, 0, 0, 640, 512, WindowHandle1)
set_display_font (WindowHandle1, 16, 'mono', 'true', 'false')
dev_display (Image)
dev_set_draw ('margin')
dev_set_line_width (3)
dev_open_window_fit_size (0, 648, RingSize, PolarResolution, 150, 512, WindowHandle)
dev_set_draw ('margin')
dev_set_line_width (3)
dev_set_color ('red')
* 
* Main loop
* 
* Detect defects in bottle necks
for Index := 1 to 16 by 1
    *讀取影象到Image
    read_image (Image, 'bottles/bottle_mouth_' + Index$'.02') 
    * 
    * Part 1: 檢測瓶子口
    auto_threshold (Image, Regions, 2)
    *通過自動閾值，選擇最黑的區域
    select_obj (Regions, DarkRegion, 1)
    opening_circle (DarkRegion, RegionOpening, 3.5)
    closing_circle (RegionOpening, RegionClosing, 25.5)
    *填充區域
    fill_up (RegionClosing, RegionFillUp)
    *找到邊界
    boundary (RegionFillUp, RegionBorder, 'outer')
    *膨脹邊界
    dilation_circle (RegionBorder, RegionDilation, 3.5)
    *取影象的邊緣，其實取的是Image 和RegionDilation的相同的部分
    reduce_domain (Image, RegionDilation, ImageReduced)
    * 
    *通過為提取的邊緣擬合一個圓來查詢瓶中心
    *canny邊緣檢測
    edges_sub_pix (ImageReduced, Edges, 'canny', 0.5, 20, 40)
    *打散成圓弧和直線
    segment_contours_xld (Edges, ContoursSplit, 'lines_circles', 5, 4, 2)
    *找出一個共同圓的部分
    union_cocircular_contours_xld (ContoursSplit, UnionContours, 0.9, 0.5, 0.5, 200, 50, 50, 'true', 1)
    *計算輪廓或者多邊形的長度
    length_xld (UnionContours, Length)
    *選擇長度最長的那一個
    *sort_index(Length)[|Length| - 1] 是取最大的長度的index,因為select_obj的index引數是從1開始的，所以需要加1
    select_obj (UnionContours, LongestContour, sort_index(Length)[|Length| - 1] + 1)
    *圓形擬合
    fit_circle_contour_xld (LongestContour, 'ahuber', -1, 0, 0, 3, 2, Row, Column, Radius, StartPhi, EndPhi, PointOrder)
    * 
    * Part 2:圓形帶變換成長方形 Transform the ring-shaped bottle neck region to a rectangle
    *建立一個圓
    gen_circle (Circle, Row, Column, Radius)
    *膨脹圓
    dilation_circle (Circle, RegionDilation, 5)
    *腐蝕圓
    erosion_circle (Circle, RegionErosion, RingSize - 5)
    *做減法
    difference (RegionDilation, RegionErosion, RegionDifference)
    *把帶狀區域的影象找出來
    reduce_domain (Image, RegionDifference, ImageReduced)
    *極座標到笛卡爾座標轉換
    polar_trans_image_ext (ImageReduced, ImagePolar, Row, Column, 0, rad(360), Radius - RingSize, Radius, PolarResolution, RingSize, 'nearest_neighbor')
    * 
    * Part 3: 通過動態閾值打到缺陷位置
    * Note the strong smoothing in x-direction in the transformed image.
    *scale_image_max應該是指正則化，找到影象最亮和最暗，然後把影象畫素拉成0-255
    scale_image_max (ImagePolar, ImageScaleMax)
    *使用平均平滑影象，後面兩個引數應該是平均視窗的大小，但是為什麼長度設定為501高為3呢，可能是因為垂直方向上差異大，想要找出垂直方向差異
    mean_image (ImageScaleMax, ImageMean, SmoothX, 3)
    *使用本地的影象動態閾值，然後分割imageSacleMax,Offset越大，找到的區域越小，因為容差大了，大於這個容差的就少了
    dyn_threshold (ImageScaleMax, ImageMean, Regions1, ThresholdOffset, 'not_equal')
    *計算連通區域
    connection (Regions1, Connection)
    *選擇高度在9~9999之間的連通區域
    select_shape (Connection, SelectedRegions, 'height', 'and', MinDefectSize, 99999)
    * ignore noise regions
    closing_rectangle1 (SelectedRegions, RegionClosing1, 10, 20)
    union1 (RegionClosing1, RegionUnion)
    * re-transform defect regions for visualization
    *把帶狀反變換為極座標影象
    polar_trans_region_inv (RegionUnion, XYTransRegion, Row, Column, 0, rad(360), Radius - RingSize, Radius, PolarResolution, RingSize, 1280, 1024, 'nearest_neighbor')
    * 
    * Part 4: Display results
    * display original image with results
    dev_set_window (WindowHandle1)
    dev_display (Image)
    dev_set_color ('blue')
    dev_display (RegionDifference)
    dev_set_color ('red')
    *XYTransRegion儲存的是影象中的瑕疵
    dev_display (XYTransRegion)
    * display polar transformed inspected region with results
    * The image and resulting region are rotated by 90 degrees
    * only for visualization purposes! (I.e. to fit better on the screen)
    * The rotation is NOT necessary for the detection algorithm.
    dev_set_window (WindowHandle)
    rotate_image (ImagePolar, ImageRotate, 90, 'constant')
    dev_display (ImageRotate)
    count_obj (RegionUnion, Number)
    if (Number > 0)
        mirror_region (RegionUnion, RegionMirror, 'diagonal', PolarResolution)
        mirror_region (RegionMirror, RegionMirror, 'row', PolarResolution)
        dev_display (RegionMirror)
        disp_message (WindowHandle1, 'Not OK', 'window', -1, -1, 'red', 'false')
    else
        disp_message (WindowHandle1, 'OK', 'window', -1, -1, 'forest green', 'false')
    endif
    if (Index < 16)
        disp_continue_message (WindowHandle1, 'black', 'true')
        stop ()
    endif
endfor