How can we extract objects from a greyscale image?

So, i got a grayscale image of a box, which contains some objects.. I need to identify if/ not the box is empty or not....
I tried using the otsu thresholding, but doesn't work properly. is it possible to convert all the other parts to black except the image of interest?

3 个评论

How do you know which part is of interest before you have done the thresholding ?
This is the image of bucket which is full. the spatula, etc are the part of interest.
I would recommend background subtraction, if you can get a picture of the empty bucket, especially if everything is taken from a fixed viewpoint (if the viewpoint is not fixed then you might need to do image registration before doing the subtraction.)

请先登录,再进行评论。

回答(1 个)

What about bwareaopen()
I = imread('example_filled2.jpg');
I1 = I < 40;
I2 = bwareaopen(I1,3e3);
imshow(I2)
What i've got
img22.png

类别

帮助中心File Exchange 中查找有关 Image Processing Toolbox 的更多信息

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by