how to place the rectangle for all the blob

Hi all,

I have 7 binary images.

anyone know how to place the rectangle for all the blob in the subplot binary images?

I used below coding, but only one binary image (the last images) have the rectangle

%% TEST IMAGES 
DATASetDir = fullfile('C:\Users\Akmal\Desktop\I-131 256 28.02.2020\I-131 SPECT NEMA VALIDATION 01112019 256X256 26.09.2021 petang');
IMAGEDir = fullfile(DATASetDir,'Test');
IMDS = imageDatastore(IMAGEDir);

%% TO GET THE VOLUME SEGMENTATION AFTER DEEP LEARNING PERFORM
alldice=[]
acc=[]
Ts = [];
Ts2 = [];

for ii=1:7
    subplot(3,3,ii)
    I = readimage(IMDS,ii);
    [C,scores] = semanticseg(I,net1);
    outt2=C=="foreground";
    st2=strel('disk',5);
    outt22 = imopen(outt2,st2);
    
    figure
    title('output')
    imshow(outt22)
    
    fprintf('\nprocess %d image\n', ii);
    T = regionprops('table', outt22,'Area','Centroid');
    info = regionprops(outt22,'Boundingbox') ;
    Ts{ii} = T;
    Ts2 = [Ts2; T];
end

allbb=[]
for k = 1 : length(info)
    BB = info(k).BoundingBox;
    rectangle('Position', [BB(1),BB(2),BB(3),BB(4)],'EdgeColor','r','LineWidth',1) ;
    allbb=[allbb; BB]
end

Answer 1

[DGM]

The second loop needs to be inside the first one, otherwise it's only going to plot the bounding boxes for the blobs in the last subplot.

[mohd akmal masud]

Sorry sir, can write for me?

[DGM]

%% TEST IMAGES 
DATASetDir = fullfile('C:\Users\Akmal\Desktop\I-131 256 28.02.2020\I-131 SPECT NEMA VALIDATION 01112019 256X256 26.09.2021 petang');
IMAGEDir = fullfile(DATASetDir,'Test');
IMDS = imageDatastore(IMAGEDir);

%% TO GET THE VOLUME SEGMENTATION AFTER DEEP LEARNING PERFORM
alldice=[]
acc=[]
Ts = [];
Ts2 = [];

for ii=1:7
    subplot(3,3,ii)
    I = readimage(IMDS,ii);
    [C,scores] = semanticseg(I,net1);
    outt2=C=="foreground";
    st2=strel('disk',5);
    outt22 = imopen(outt2,st2);
    
    title('output')
    imshow(outt22)
    
    fprintf('\nprocess %d image\n', ii);
    T = regionprops('table', outt22,'Area','Centroid');
    info = regionprops(outt22,'Boundingbox') ;
    Ts{ii} = T;
    Ts2 = [Ts2; T];
    
    allbb=[];
    for k = 1 : length(info)
        BB = info(k).BoundingBox;
        rectangle('Position', [BB(1),BB(2),BB(3),BB(4)],'EdgeColor','r','LineWidth',1);
        allbb=[allbb; BB];
    end
end

[mohd akmal masud]

its work sir...tq very much..

But now I want to calculated all the sum voxel for sphere 1, sphere 2, sphere 3, sphere 4. I used this code below, but it only calculated for one image (4 circle), how to calculated for circle for all images?

T = regionprops('table', outt22,'Area','Centroid')

T =

  4×2 table

    Area        Centroid    
    ____    ________________

     15     105.73    132.53
     21     126.52    145.38
     64     147.12    108.86
     31     147.42     133.9

[Image Analyst]

Are the blobs always in the same position, or do they move around (so that blob 1 in one image might be blob 2 in another image)? If they're fairly stable you can just make an array of areas in a loop over all your images.

Something like (untested)

areaSum = zeros(4, 1); % Initialize before loop.
for ii = 1 : 7 % For all 7 images.
    T = whatever...
    % Then inside your loop over ii, sum up area of each of the 4 blobs.
    areaSum = areaSum + T.Area; % A 4 by 1 column vector.  Each element is the sum of each blob's area.

[mohd akmal masud]

yah, same position

[mohd akmal masud]

sorry sir, can you write more details. what is T.Area?

[Star Strider]

‘T’ is a table, and the ‘T.Area’ reference returns the values in the ‘Area’ variable as a column vector.

.

Answer 2

[yanqi liu]

%% TEST IMAGES
DATASetDir = fullfile('C:\Users\Akmal\Desktop\I-131 256 28.02.2020\I-131 SPECT NEMA VALIDATION 01112019 256X256 26.09.2021 petang');
IMAGEDir = fullfile(DATASetDir,'Test');
IMDS = imageDatastore(IMAGEDir);
%% TO GET THE VOLUME SEGMENTATION AFTER DEEP LEARNING PERFORM
alldice=[]
acc=[]
Ts = [];
Ts2 = [];
for ii=1:7
    I = readimage(IMDS,ii);
    [C,scores] = semanticseg(I,net1);
    outt2=C=="foreground";
    st2=strel('disk',5);
    outt22 = imopen(outt2,st2);
    
    figure(ii)
    title('output')
    imshow(outt22)
    
    fprintf('\nprocess %d image\n', ii);
    T = regionprops('table', outt22,'Area','Centroid');
    info = regionprops(outt22,'Boundingbox') ;
    Ts{ii} = T;
    Ts2 = [Ts2; T];
end
allbb=[]
for ii=1:7
    figure(ii);
    hold on;
    for k = 1 : length(info)
        BB = info(k).BoundingBox;
        rectangle('Position', [BB(1),BB(2),BB(3),BB(4)],'EdgeColor','r','LineWidth',1) ;
        allbb=[allbb; BB]
    end
end

[mohd akmal masud]

Error using info
Too many output arguments.