Query regarding colour thresholder and mask formed

i have been trying to extraxt the number of pixels in the image that adhere to the hsv colour channel thresholds given by colour thresholder toolbox. The thresholds were obtained from the function generated by the toolbox itself and even then, according to my understanding, the number of pixels that pass the threshold is coming up as 0.

this is the image i used

this is what the colour thresholder looked like at the end

and this is the function that was generated:

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
%  minimum/maximum values for each channel of the colorspace were set in the
%  App and result in a binary mask BW and a composite image maskedRGBImage,
%  which shows the original RGB image values under the mask BW.

% Auto-generated by colorThresholder app on 25-May-2020
%------------------------------------------------------


% Convert RGB image to chosen color space
I = rgb2hsv(RGB);

% Define thresholds for channel 1 based on histogram settings
channel1Min = 0.616;
channel1Max = 0.696;

% Define thresholds for channel 2 based on histogram settings
channel2Min = 0.495;
channel2Max = 1.000;

% Define thresholds for channel 3 based on histogram settings
channel3Min = 0.613;
channel3Max = 1.000;

% 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

As i did not want to use a function, this is how i tweaked the code inorder to count the number of pixels that pass the threshold:

EyeDetect = vision.CascadeObjectDetector('EyePairBig');
FaceDetect = vision.CascadeObjectDetector();


    B= imread('C:\Users\0wner\Desktop\VIT\image processing\project\cmyk.jpg');
   data= imsharpen(B,'Radius',1,'Amount',2);
    %I=imread('C:\Users\0wner\Desktop\CBIR project\dataset\normal\000002.jpg');
   % BB=step(FaceDetect,I);

    %for j= 1:size(BB,1)
        %face = imcrop(I, BB(j,:));
    %end
    
    BB = step(FaceDetect,data);
    for j=1:size(BB,1)
        I= imcrop(data, BB(j,:));
    end


    EE=step(EyeDetect,data);

    for k= 1:size(EE,1)
        eye = imcrop(data, EE(k,:));
    end
    new_eye_image= rgb2hsv(eye);
    %imshow(new_eye_image);

    ewp=0;
    %perc_wrinkle=0;
    %perc_fwrinkle=0;
    %if cyan pixel found, pixel with eye wrinkle. calculate percentage of eye
    %wrinkle
% Define thresholds for channel 1 based on histogram settings
channel1Min = 0.620;
channel1Max = 0.667;

% Define thresholds for channel 2 based on histogram settings
channel2Min = 0.489;
channel2Max = 1.000;

% Define thresholds for channel 3 based on histogram settings
channel3Min = 0.568;
channel3Max = 1.000;
[rows, columns, numberOfColorChannels] = size(new_eye_image);
    for x=1:rows
        for y=1:columns
            pixel= new_eye_image(x,y);
            if(((pixel(:,:,1) >= channel1Min ) && (pixel(:,:,1) <= channel1Max)) && ...
    ((pixel(:,:,2) >= channel2Min ) && (pixel(:,:,2) <= channel2Max)) && ...
    ((pixel(:,:,3) >= channel3Min ) && (pixel(:,:,3) <= channel3Max)))
                ewp = ewp+1;
            end 
        end
    end
    

the values of ewp always turn up as zero. Even the maskedRGBImage comes out as a zero matrix. How is this possible?

Answer 1

[Image Analyst]

You forgot to give the third dimension when you got pixel. Try this:

for row=1:rows
	for col=1:columns
		pixel = new_eye_image(row, col, :);
		if(((pixel(:,:,1) >= channel1Min ) && (pixel(:,:,1) <= channel1Max)) && ...
				((pixel(:,:,2) >= channel2Min ) && (pixel(:,:,2) <= channel2Max)) && ...
				((pixel(:,:,3) >= channel3Min ) && (pixel(:,:,3) <= channel3Max)))
			ewp = ewp+1;
		end
	end
end
fprintf('ewp = %d\n', ewp);