Clever Geek Handbook

Removing Objects from an Image Using MATLAB

I tried to extract a road from a map based on color intensity, but I could not segment the roads clearly as some buildings have the same intensity as some of the roads. Now I am trying to remove these buildings. To do this, I'm trying to use the idea of ​​a "maximum inscribed circle" in the object, since the inscribed circle in the building will be larger than the road. However, I cannot do this with my attempts yet. Here is the code I wrote.

clc
clear all
x=imread('http://i.imgur.com/R80JmEH.jpg?1');
x1=rgb2gray(x);
imshow(x1)
x1(x1<240)=0;
T=graythresh(x1);
y=im2bw(x1,T);
figure;imshow(y)
y1= imfill(y,'holes');
figure; imshow(y1)
BW2 = bwareaopen(y1,10);
figure;imshow(BW2);
s = regionprops(BW2, x1, {'Centroid','WeightedCentroid'});
figure;imshow(BW2)
title('Weighted (red) and Unweighted (blue) Centroid Locations');
hold on
numObj = numel(s);
for k = 1 : numObj
plot(s(k).WeightedCentroid(1), s(k).WeightedCentroid(2), 'r*');
plot(s(k).Centroid(1), s(k).Centroid(2), 'bo');
end
hold off

Original Image:

original image

Red areas to be removed:

red circled area should be removed

+3


source to share


1 answer


Try using the property Extent

regionprops

. Here are some preliminary results:

clc
clear all
img=imread('map.JPG');
img=rgb2gray(img);
img(img<200) = 255;
figure(1), imshow(img);
img(img<240) = 0; 
img=im2bw(img);
figure(2),imshow(img);

img = imfill(img,'holes');
img = imerode(img,strel('disk',1));
figure(3),imshow(img)

cc = bwconncomp(img);
l = labelmatrix(cc);
rp = regionprops(cc,'Extent');
idx = ([rp.Extent] < .2);
img_filt = ismember(l,find(idx));
figure(4), imshow(img_filt,[]);


enter image description here

+3


source






More articles:


All Articles