Can morphology.remove_small_objects be used to remove small noise?

Question

My binary image has lots of noise (small white blobs about 3-6 pixels in area). Can the function skimage.morphology.remove_small_objects() be used to remove these small blobs?

In my experimentation, the function leaves the image unchanged. Am I using the function incorrectly or is the function not suited to what I want to achieve?

src = cv2.imread('plan4.png')
src = cv2.GaussianBlur(src, (3,3), 1)

edges = get_edges(src.copy())

noise_reduced = morphology.remove_small_objects(edges .copy(), 2,)

cv2.imshow('src', src)
cv2.imshow('noise_reduced', noise_reduced)
cv2.imshow('edges ', edges )

Below is the original with small white blobs (that I want to remove) and the result of remove_small_objects() notice they are the same and no blobs are removed. *Note: morphological closing or opening the image would remove these small blobs but it also degrades my lines too much. I really prefer finding blobs whose area is ~6 pixels and deleting those.

Answer 1

When you pass in an integer image, scikit-image assumes that all the same-valued pixels belong to the same object, even if they are not connected. So, in your case, all the pixels are considered part of the same (big) object, so none are removed. Instead, you should do use

from skimage.measure import label

noise_reduced = morphology.remove_small_objects(label(edges), 2,)

Hope this helps!