In this article, we will see how we can set the element structure for erode of the image in mahotas. Erosion (usually represented by ?) is one of two fundamental operations (the other being dilation) in morphological image processing from which all other morphological operations are based. It was originally defined for binary images, later being extended to grayscale images, and subsequently to complete lattices. In order to erode the image we use mahotas.morph.erode method.
In this tutorial, we will use “luispedro” image, below is the command to load it.
mahotas.demos.load('luispedro')
Below is the luispedro image
Below is the default structure of the element for erosion, which a 1 cross
np.array([
[0, 1, 0],
[1, 1, 1],
[0, 1, 0]],
bool)
Below is the implementation
Python3
# importing required librariesimport mahotasimport mahotas.demosfrom pylab import gray, imshow, showimport numpy as np# loading imageluispedro = mahotas.demos.load('luispedro')# filtering imageluispedro = luispedro.max(2)# otsu methodT_otsu = mahotas.otsu(luispedro) # image values should be greater than otsu valueimg = luispedro > T_otsuprint("Image threshold using Otsu Method")# showing imageimshow(img)show()# erode structurees = np.array([ [1, 1, 1], [1, 1, 1], [1, 1, 1]], bool)# eroding image using element structurenew_img = mahotas.morph.erode(img, es)# showing dilated imageprint("Eroded Image")imshow(new_img)show() |
Output :
Image threshold using Otsu Method
Eroded Image
Another example
Python3
# importing required librariesimport mahotasimport numpy as npimport matplotlib.pyplot as pltimport os # loading imageimg = mahotas.imread('dog_image.png') # setting filter to the imageimg = img[:, :, 0]# otsu methodT_otsu = mahotas.otsu(img) # image values should be greater than otsu valueimg = img > T_otsuprint("Image threshold using Otsu Method")# showing imageimshow(img)show()# erode structurees = np.array([ [0, 0, 0], [0, 1, 0], [0, 0, 0]], bool)# eroding image using element structurenew_img = mahotas.morph.erode(img, es)# showing dilated imageprint("Eroded Image")imshow(new_img)show() |
Output :
Image threshold using Otsu Method
Eroded Image
