SVM classifier with sliding window
    조회 수: 4 (최근 30일)
  
       이전 댓글 표시
    
Helloo!!
I am working on detecting eyes open or close by using SVM classifier with HOG feature and there is problem in running the sliding window and do not know what is the mistake.
as you see the code below , i have already trained SVM classifier. 
can anyone help me! please 
code:
load classifier 
imdsTest = imageDatastore('TestImages');
testImg = readimage(imdsTest,1);
figure, 
imshow(testImg)
title('Test Image');
%% 
s = 5;
w = 100;
h = 40;
[r,c] = size(testImg);
H = zeros(r,c);
r = floor((r-h)/s)+1;
c = floor((c-w)/s)+1;
%%
r1 = 1;
c1 = 1;
for n=1:r
    for m=1:c
        img = testImg (c1:c1+39,r1:r1+99);
        %imshow(img)
        hog1 = extractHOGFeatures(img,'CellSize',[2,2]);
        [pred,scores] = predict(classifier,hog1);
        if (string(pred) == 'closedEye')
            pause(1);
            H(c1,r1) = - scores(2);
        end 
        r1 = r1+s;
    end    
    r1 = 1;
    c1 = c1 +s;
end    
[rw,c1]= find(H>0.75);
figure, 
imshow(testImg)
title('closed eye Detection')
for d=1:length(rw)
    pasue(1)
    imrect(gca, [c1(d), rw(d),100,40]); %
end
댓글 수: 1
답변 (0개)
참고 항목
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!