Help me to resolve this Error In My GUI ( I am doing hand signal recognition) - An empty cluster error occurred in every replicate.
1 visualización (últimos 30 días)
Mostrar comentarios más antiguos
I already made the GUI and snapshot working well, meanwhile sometimes I got this error can some1 explain it to me why?
THIS IS THE ERROR
??? Error using ==> kmeans at 382
An empty cluster error occurred in every replicate.
Error in ==> segmentizeImage1 at 12
[cluster_idx cluster_center] = kmeans(ab,nColors,'distance','sqEuclidean', ...
Error in ==> bui_simple>start_snap_Callback at 108
segmentizeImage1;
Error in ==> gui_mainfcn at 96
feval(varargin{:});
Error in ==> bui_simple at 42
gui_mainfcn(gui_State, varargin{:});
Error in ==>
@(hObject,eventdata)bui_simple('start_snap_Callback',hObject,eventdata,guidata(hObject))
??? Error while evaluating uicontrol Callback
REFER THE CODE BELOW ( I used it to track and crop the hand automatically):
warning off stats:kmeans:EmptyCluster;
rawImage = x; %x = is the image taken on snapshot
I = rawImage;
cform = makecform('srgb2lab');
J = applycform(I,cform);
ab = double(J(:,:,2:3));
nrows = size(ab,1);
ncols = size(ab,2);
ab = reshape(ab,nrows*ncols,2);
nColors = 2;
[cluster_idx cluster_center] = kmeans(ab,nColors,'distance','sqEuclidean', ...
'Replicates',2);
pixel_labels = reshape(cluster_idx,nrows,ncols);
segmented_images = cell(1,2);
rgb_label = repmat(pixel_labels,[1 1 3]);
for k = 1:nColors
color = I;
color(rgb_label ~= k) = 0;
segmented_images{k} = color;
end
mean_cluster_value = mean(cluster_center,2);
[tmp, idx] = sort(mean_cluster_value);
hand_cluster_num = idx(2);
K = segmented_images{hand_cluster_num};
L = im2bw(segmented_images{hand_cluster_num},0.000);
s = regionprops(rgb_label, I, {'Centroid','BoundingBox'});
% s(hand_cluster_num).Centroid
% s(hand_cluster_num).BoundingBox
centroid_x = uint16(s(hand_cluster_num).Centroid(1));
centroid_y = uint16(s(hand_cluster_num).Centroid(2));
cropped_x = uint16(s(hand_cluster_num).BoundingBox(1))+1;
cropped_y = uint16(s(hand_cluster_num).BoundingBox(2))+1;
cropped_w = uint16(s(hand_cluster_num).BoundingBox(4))-2;
cropped_h = uint16(s(hand_cluster_num).BoundingBox(5))-2;
% apply gaussian blur to remove noise
PSF = fspecial('gaussian',7,10);
L = imfilter(L,PSF,'symmetric','conv');
% cropped region of interest from main image
M = L( cropped_y : (cropped_y+cropped_h), cropped_x: (cropped_x+cropped_w) );
% trim leading and leading zeroes
M(:, logical(sum(abs(M)) == 0)) = [];
cropped_h = size(M,1);
cropped_w = size(M,2);
non_zeroes = find(sum(abs(L))~=0);
cropped_x = non_zeroes(1);
% fill holes to remove flares
M = imfill(M, 'holes');
y = M;
z = imresize(y, [40 30]);
z = z(:);
2 comentarios
Image Analyst
el 13 de Feb. de 2012
We can't really replicate your code. Just check the inputs to kmeans() and make sure they are all proper.
Respuestas (0)
Ver también
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!