When I call mahotas.features.zernike_moments
on certain images containing very irregular shapes I get the following error:
fv = mahotas.features.zernike_moments(mask, cv2.minEnclosingCircle(cnt)[1], degree=8)
File "C:\Users\admin\AppData\Local\Programs\Python\Python37\lib\site-packages\mahotas\features\zernike.py", line 59, in zernike_moments
c0,c1 = center_of_mass(im)
ValueError: too many values to unpack (expected 2)
It works on simple shapes like below:
But I get the error on the below image with the following code. Any idea what I am doing wrong?
penStrokes = np.array(penStrokes)
peri = cv2.arcLength(penStrokes, True)
approx = cv2.approxPolyDP(penStrokes, 0.02 * peri, True)
mask = np.zeros((frame.shape[0], frame.shape[1], 1), dtype='uint8')
cv2.drawContours(mask, [approx], -1, (255,), -1)
cnt = cv2.findContours(mask.copy(), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)[1][0]
cv2.imshow('mask', mask)
# Determine shape from zernike moments
fv = mahotas.features.zernike_moments(mask, cv2.minEnclosingCircle(cnt)[1], degree=8)
print(fv)
Edit It seems if I resize the mask to 500 pixels wide the code works? Does mahotas have a minimum size the shape needs to be?
Author of mahotas here.
mask
is a 3-D image (although the last dimension is1
), while the function only works for 1-D images. Try: