Segmenting Colors in an RBG image

Question

Kate Heinzman 2020-2-12

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/505187-segmenting-colors-in-an-rbg-image

编辑： KSSV 2020-2-13

I originally used color segmentation using kmeans clustering to try to isolate the specific cell colors I'm trying to get out of the code.

My code looks like this:

i

mage = imread('cells.jpg');
image = image(:,:,1:3);
% Convert image from rbg to L*a*b* color space
lab_image = rgb2lab(image);
%% K-Means Clustering 
% Since the color information exists in the 'a*b*' color space, 
% your objects are pixels with 'a*' and 'b*' values.
ab = lab_image(:,:,2:3);
% Convert the data to data type single for use with imsegkmeans.
ab = im2single(ab);
pixel_labels = imsegkmeans(ab,2);
% For every object in your input, imsegkmeans returns an index, or a label, 
% corresponding to a cluster. 
% Using pixel_labels, you can separate objects in image by color
mask1 = pixel_labels == 1;
cluster1 = Ki67 .* uint8(mask1);
imshow(cluster1,[]);
cluster_mask = bwareaopen(cluster1,300); %removing noise pixels
noise_cluster = Ki67 .* uint8(cluster_mask);
imshow(noise_cluster);
imshowpair(cluster1,noise_cluster,'montage');

The image above is the original image. The image below is what I get after using the code. I only want the dark brown cells, so how do I isolate the dark brown cells? Also if you know how to be able to count the dark brown cells once they're isolated that would be great.