How to detect unstructered objects in an image ?
2 vues (au cours des 30 derniers jours)
Afficher commentaires plus anciens
Ender Rencuzogullari
le 19 Mai 2018
Modifié(e) : Ender Rencuzogullari
le 20 Mai 2018
Hi,
I have an RGB image which has black objects on it to detect, find center of it and label with a circle. I applied some proccesses on it but cannot achieve. Here is the steps that I have applied:
Original Image:
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/190668/image.jpeg)
Step 1:
image = imread('Im_005.jpg');
I = rgb2gray(image);
J = imresize(I, 0.5);
E = histeq(J);
figure(4), imshow(E)
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/190669/image.jpeg)
Step 2:
bw = imbinarize(E);
se3 = strel('disk',1);
dilation = imdilate(bw,se3);
figure(5),imshow(dilation)
cc = bwconncomp(dilation, 8);
cc.NumObjects;
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/190670/image.jpeg)
However, although I have tried lots of method (morphological etc.), I could not figure out how to find the center points of black objects and label them with a circle. Also,
cc = bwconncomp(dilation, 4);
gives output as "number of objects: 1" although there are two objects. How can I solve this problem?
Best.
0 commentaires
Réponse acceptée
Image Analyst
le 19 Mai 2018
Use regionprops():
dilation = ~imdilate(bw,se3);
props = regionprops(dilation, 'Centroid');
1 commentaire
Plus de réponses (0)
Voir également
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!