【dyn_threshold_划痕检测】


总结:

  • 灰度低通滤波可以突出信号。
  • dyn_threshold可以对两幅孪生图的信号进行阈值分割。

一、dyn_threshold算子说明

dyn_threshold(OrigImage, ThresholdImage : RegionDynThresh : Offset, LightDark : )

  • dyn_threshold 从输入的两幅图像中选择像素满足阈值条件的区域。
  • 令 g_{o} = g_{OrigImage} 和 g_{t} = g_{ThresholdImage}。
  • 其中,g_{OrigImage}是原始图像,g_{ThresholdImage}是平滑后图像,充当阈值。

那么

1) LightDark = ‘light’ 的条件是:

在这里插入图片描述
2)对于 LightDark = ‘dark’,条件是:

在这里插入图片描述

3)对于 LightDark = ‘equal’,条件是:

在这里插入图片描述
4)对于 LightDark = ‘not_equal’,条件是:

在这里插入图片描述

通常,阈值图像是原始图像的平滑版本(例如,通过应用 mean_image、binomial_filter、gauss_filter 等)。那么 dyn_threshold 的效果类似于将阈值应用于原始图像的高通滤波版本(参见 highpass_image)。

二、针对问题:

2.1 原始图片

如下图中,将划痕部分检出来。

read_image (Image, 'surface_scratch')

在这里插入图片描述

  • 原始图的表面灰度图(看不出明显的划痕)。

2.2 平滑后的图片

mean_image (Image, ImageMean, 7, 7)

平滑图片灰度图(划痕明显):

在这里插入图片描述

2.3 观察结果

可以断定,平滑图片中,能够将被噪声湮灭的细长划痕的信号给暴露出来。

三、代码部分

* This programm shows the extraction of surface scratches via
* local thresholding and morphological post-processing
* 
dev_update_off ()
dev_close_window ()
* 
* Step 1: Acquire image
* 
read_image (Image, 'surface_scratch')
get_image_size (Image, Width, Height)
dev_open_window_fit_image (Image, 0, 0, Width, Width, WindowID)
set_display_font (WindowID, 16, 'mono', 'true', 'false')
dev_set_draw ('margin')
dev_set_line_width (4)
dev_display (Image)
Message := 'This program shows the extraction of'
Message[1] := 'surface scratches via local thresholding'
Message[2] := 'and morphological post-processing'
disp_message (WindowID, Message, 'window', 12, 12, 'black', 'true')
disp_continue_message (WindowID, 'black', 'true')
stop ()
* 
* Step 2: Segment image
* 
* Using a local threshold
mean_image (Image, ImageMean, 7, 7)
dyn_threshold (Image, ImageMean, DarkPixels, 5, 'dark')
* 
* Extract connected components
connection (DarkPixels, ConnectedRegions)
dev_set_colored (12)
dev_display (Image)
dev_display (ConnectedRegions)
Message := 'Connected components after image segmentation'
Message[1] := 'using a local threshold.'
disp_message (WindowID, Message, 'window', 12, 12, 'black', 'true')
disp_continue_message (WindowID, 'black', 'true')
stop ()
* 
* Step 3: Process regions
* 
* Select large regions
select_shape (ConnectedRegions, SelectedRegions, 'area', 'and', 10, 1000)
dev_display (Image)
dev_display (SelectedRegions)
disp_message (WindowID, 'Large Regions', 'window', 12, 12, 'black', 'true')
disp_continue_message (WindowID, 'black', 'true')
stop ()
* 
* Visualize fractioned scratch
dev_open_window (0, 0, Width, Height, 'black', WindowHandle)
*open_zoom_window (0, round(Width / 2), 2, 303, 137, 496, 3, WindowHandleZoom)
dev_set_color ('blue')
dev_display (Image)
dev_display (SelectedRegions)
set_display_font (WindowHandle, 16, 'mono', 'true', 'false')
disp_message (WindowHandle, 'Fractioned scratches', 'window', 12, 12, 'black', 'true')
disp_continue_message (WindowHandle, 'black', 'true')
stop ()
* 
* Merge fractioned scratches via morphology
union1 (SelectedRegions, RegionUnion)
dilation_circle (RegionUnion, RegionDilation, 3.5)
dev_display (Image)
dev_display (RegionDilation)
Message := 'Region of the scratches after dilation'
disp_message (WindowHandle, Message, 'window', 12, 12, 'black', 'true')
disp_continue_message (WindowHandle, 'black', 'true')
stop ()
skeleton (RegionDilation, Skeleton)
connection (Skeleton, Errors)
dev_set_colored (12)
dev_display (Image)
dev_display (Errors)
Message := 'Fractioned scratches merged via morphology'
disp_message (WindowHandle, Message, 'window', 12, 12, 'black', 'true')
disp_continue_message (WindowHandle, 'black', 'true')
stop ()
* 
* Distinguish small and large scratches
dev_close_window ()
*close_zoom_window (WindowHandle, Width, Height)
select_shape (Errors, Scratches, 'area', 'and', 50, 10000)
select_shape (Errors, Dots, 'area', 'and', 1, 50)
dev_display (Image)
dev_set_color ('red')
dev_display (Scratches)
dev_set_color ('blue')
dev_display (Dots)
Message := 'Extracted surface scratches'
Message[1] := 'Not categorized as scratches'
disp_message (WindowID, Message, 'window', 440, 310, ['red','blue'], 'true')

检查结果:
在这里插入图片描述

总结:

  • 灰度低通滤波可以突出信号。
  • dyn_threshold可以对两幅孪生图的信号进行阈值分割。

猜你喜欢

转载自blog.csdn.net/weixin_42483745/article/details/126952396