Using same thresholding in different images to create binary
1 次查看(过去 30 天)
显示 更早的评论
Hello all,
I am on the process to analyze RGB pictures of grass cover. We grew the grass homogeneusly before applying some treatments. I used the color thresholding app to create threshold for the baseline (homogeneous cover) filtering out small black spaces between leaves and consider all the rest as green. From this I extracted this code:
function [BW,maskedRGBImage] = createMask(RGB)
%createMask Threshold RGB image using auto-generated code from colorThresholder app.
% [BW,MASKEDRGBIMAGE] = createMask(RGB) thresholds image RGB using
% auto-generated code from the colorThresholder app. The colorspace and
% range for each channel of the colorspace were set within the app. The
% segmentation mask is returned in BW, and a composite of the mask and
% original RGB images is returned in maskedRGBImage.
% Auto-generated by colorThresholder app on 17-Mar-2023
%------------------------------------------------------
% Convert RGB image to chosen color space
I = RGB;
% Define thresholds for channel 1 based on histogram settings
channel1Min = 35.000;
channel1Max = 109.000;
% Define thresholds for channel 2 based on histogram settings
channel2Min = 50.000;
channel2Max = 149.000;
% Define thresholds for channel 3 based on histogram settings
channel3Min = 23.000;
channel3Max = 131.000;
% Create mask based on chosen histogram thresholds
sliderBW = (I(:,:,1) >= channel1Min ) & (I(:,:,1) <= channel1Max) & ...
(I(:,:,2) >= channel2Min ) & (I(:,:,2) <= channel2Max) & ...
(I(:,:,3) >= channel3Min ) & (I(:,:,3) <= channel3Max);
BW = sliderBW;
% Initialize output masked image based on input image.
maskedRGBImage = RGB;
% Set background pixels where BW is false to zero.
maskedRGBImage(repmat(~BW,[1 1 3])) = 0;
end
Now I want to use those treshold to identify green area in the treatments. Some grass is alive and green some other dead and brown. How can I apply this threshold to other images to have binary of them all so I can transform them in a matrix for further analysis? Is there any color detection app or code I can use?
Thank you all in advance for any suggestion.
Cheers
0 个评论
回答(1 个)
Ranjeet
2023-4-12
Hi Enrico,
Since, you already have exported the createMask function by thresholding a baseline image having grass cover, you can use the function with other RGB images as the output of the function is a binary (BW) along with RGB (maskedRGBImage) image.
Here is a mask function that I exported by using some example images with grass cover and tuned to filter green patches, you may use this or try experimenting with the Color Thresholder App.
function [BW,maskedRGBImage] = createMask(RGB)
%createMask Threshold RGB image using auto-generated code from colorThresholder app.
% [BW,MASKEDRGBIMAGE] = createMask(RGB) thresholds image RGB using
% auto-generated code from the colorThresholder app. The colorspace and
% range for each channel of the colorspace were set within the app. The
% segmentation mask is returned in BW, and a composite of the mask and
% original RGB images is returned in maskedRGBImage.
% Auto-generated by colorThresholder app on 11-Apr-2023
%------------------------------------------------------
% Convert RGB image to chosen color space
I = RGB;
% Define thresholds for channel 1 based on histogram settings
channel1Min = 38.000;
channel1Max = 187.000;
% Define thresholds for channel 2 based on histogram settings
channel2Min = 82.000;
channel2Max = 255.000;
% Define thresholds for channel 3 based on histogram settings
channel3Min = 0.000;
channel3Max = 188.000;
% Create mask based on chosen histogram thresholds
sliderBW = (I(:,:,1) >= channel1Min ) & (I(:,:,1) <= channel1Max) & ...
(I(:,:,2) >= channel2Min ) & (I(:,:,2) <= channel2Max) & ...
(I(:,:,3) >= channel3Min ) & (I(:,:,3) <= channel3Max);
BW = sliderBW;
% Initialize output masked image based on input image.
maskedRGBImage = RGB;
% Set background pixels where BW is false to zero.
maskedRGBImage(repmat(~BW,[1 1 3])) = 0;
end
0 个评论
另请参阅
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!