Segment Image and Save as New Picture

Assuming I can segment an image using a process like this: Texture Segmentation Using Gabor Filters - MATLAB & Simulink (mathworks.com)

How can I save the image of the segmented dog (see bottom of that link) and save into a jpg? Without the black background, just the dog itself?

Answer 1

[yanqi liu]

sir，please check the follow code to get some information

for more information,you can read the book 《计算机视觉与深度学习实战》，Thank you！

clc; clear all; close all;
A = imread('kobi.png');
A = imresize(A,0.25);
Agray = rgb2gray(A);

imageSize = size(A);
numRows = imageSize(1);
numCols = imageSize(2);

wavelengthMin = 4/sqrt(2);
wavelengthMax = hypot(numRows,numCols);
n = floor(log2(wavelengthMax/wavelengthMin));
wavelength = 2.^(0:(n-2)) * wavelengthMin;

deltaTheta = 45;
orientation = 0:deltaTheta:(180-deltaTheta);

g = gabor(wavelength,orientation);

gabormag = imgaborfilt(Agray,g);

for i = 1:length(g)
    sigma = 0.5*g(i).Wavelength;
    K = 3;
    gabormag(:,:,i) = imgaussfilt(gabormag(:,:,i),K*sigma); 
end

X = 1:numCols;
Y = 1:numRows;
[X,Y] = meshgrid(X,Y);
featureSet = cat(3,gabormag,X);
featureSet = cat(3,featureSet,Y);

numPoints = numRows*numCols;
X = reshape(featureSet,numRows*numCols,[]);

X = bsxfun(@minus, X, mean(X));
X = bsxfun(@rdivide,X,std(X));

coeff = pca(X);
feature2DImage = reshape(X*coeff(:,1),numRows,numCols);
figure
imshow(feature2DImage,[])

L = kmeans(X,2,'Replicates',5);
L = reshape(L,[numRows numCols]);
figure
imshow(label2rgb(L))

L = reshape(L,[numRows numCols]);
figure
imshow(label2rgb(L))

Aseg1 = zeros(size(A),'like',A);
Aseg2 = zeros(size(A),'like',A);
BW = L == 2;
BW = ~BW;
BW = bwareafilt(BW,1);
if BW(round(size(BW,1)/2), round(size(BW,2)/2))==0
    BW = ~BW;
end
[r,c] = find(BW);
A1 = A(:,:,1); A2 = A(:,:,2); A3 = A(:,:,3);
A1(~BW) = 255;
A2(~BW) = 255;
A3(~BW) = 255;
B = cat(3, A1, A2, A3);
B = B(min(r):max(r),min(c):max(c),:);
figure; imshow(B);

% save
imwrite(mat2gray(B), 'result.png');

Answer 2

[DGM]

You can't have an image of "just the dog", in the sense that the image must be a rectangular array. The background must be something. You can fill it with a solid color, or probably what you intend is to use an alpha mask to make the background transparent.

inpict = imread('coins.png');
mask = imread('coinmask.png');

imshow(inpict)

clf % to reset web-view
imshow(mask)

imwrite(inpict,'transparentimg.png','alpha',double(mask))

Imshow(), etc doesn't handle transparent image display.