Logo Questions Linux Laravel Mysql Ubuntu Git Menu
 

How to get a rectangular subimage from regionprops(Image,'BoundingBox') in Matlab?

I have some particles that I've identified in a larger image, and need to parse into smaller images for each particle. I've used the regionprops 'BoundingBox' function, but haven't been successful yet. How can I now make a rectangular subimage of image I using BoundingBox? I can use BoundingBox to draw a rectangle on the original image, but the parameters returned by BoundingBox seem not to be of pixel dimension (x,y, width, height), (x1, y1, x2, y2), etc, which I would expect a bounding box to return. I've written some sample code using coins.png to make it easier for anyone to understand. Can you help me with this? Thanks!

figure(1);
I = imread('coins.png');
bw = im2bw(I, graythresh(I));
bw2 = imfill(bw,'holes');
imshow(bw2);


figure(2);
L = bwlabel(bw2);
imshow(label2rgb(L, @jet, [.7 .7 .7]))

figure(3);
imshow(I);
s = regionprops(L, 'BoundingBox');
rectangle('Position', s(1).BoundingBox);
like image 510
user391339 Avatar asked Oct 29 '11 16:10

user391339


People also ask

How do you find the coordinates of a bounding box in a picture?

To make coordinates normalized, we take pixel values of x and y, which marks the center of the bounding box on the x- and y-axis. Then we divide the value of x by the width of the image and value of y by the height of the image. width and height represent the width and the height of the bounding box.

How do you crop an image from the bounding box in Matlab?

Q = imread('IMG_1800. jpg'); bound = regionprops(Q, 'BoundingBox'); subImage = imcrop(Q, bound);


2 Answers

According to the documentation of REGIONPROPS:

BoundingBox is [ul_corner width], where:

  • ul_corner: is in the form [x y z ...] and specifies the upper-left corner of the bounding box

  • width: is in the form [x_width y_width ...] and specifies the width of the bounding box along each dimension

Now you can use IMCROP functions as imcrop(I, rect) where:

rect is a four-element position vector [xmin ymin width height] that specifies the size and position of the crop rectangle.

Thus:

s = regionprops(L, 'BoundingBox');

subImage = imcrop(I, s(1).BoundingBox);
imshow(subImage)
like image 115
Amro Avatar answered Sep 29 '22 17:09

Amro


The parameters returned by regionprops are [y,x,width,height] in matrix coordinates (see also "unexpected Matlab".

Thus, to extract the rectangle, you write:

subImage = I(round(s(1).BoundingBox(2):s(1).BoundingBox(2)+s(1).BoundingBox(4)),...
       round(s(1).BoundingBox(1):s(1).BoundingBox(1)+s(1).BoundingBox(3)));
like image 21
Jonas Avatar answered Sep 29 '22 16:09

Jonas