Mahotas – Perimeter of Objects in binary image

Last Updated : 15 Mar, 2023

In this article we will see how we can get the perimeter of objects in binary images in mahotas. For this we are going to use the fluorescent microscopy image from a nuclear segmentation benchmark. We can get the image with the help of command given below

mahotas.demos.nuclear_image()

Below is the nuclear_image

A pixel is part of an object perimeter if its value is one and there is at least one zero-valued pixel in its neighborhood. By default the neighborhood of a pixel is 4 nearest pixels, but if we can set it to 8 then 8 nearest pixels will be considered.
In order to do this we will use mahotas.labelled.bwperim method

Syntax : mahotas.labeled.bwperim(image, n)
Argument : It takes numpy.ndarray object i.e labelled image preferred black and white and integer i.e nearest pixels which is optional
Return : It returns numpy.ndarray object i.e a boolean image

Note : The input of the this should be the filtered image object which is labelled
In order to filter the image we will take the image object which is numpy.ndarray and filter it with the help of indexing, below is the command to do this

image = image[:, :, 0]

Example 1 :

Python3

# importing required libraries
import mahotas
import numpy as np
from pylab import imshow, show
import os
 
# loading nuclear image
f = mahotas.demos.load('nuclear')
 
# setting filter to the image
f = f[:, :, 0]
 
# setting gaussian filter
f = mahotas.gaussian_filter(f, 4)
 
# setting threshold value
f = (f> f.mean())
 
# creating a labelled image
labelled, n_nucleus = mahotas.label(f)
 
 
# showing the labelled image
print("Labelled Image")
imshow(labelled)
show()
 
# getting perimeters
relabelled = mahotas.labelled.bwperim(labelled)
 
 
# showing the image
print("Perimeters Image")
imshow(relabelled)
show()

Output :

Example 2 :

Python3

# importing required libraries
import numpy as np
import mahotas
from pylab import imshow, show
  
# loading image
img = mahotas.imread('dog_image.png')
    
# filtering the image
img = img[:, :, 0]
     
# setting gaussian filter
gaussian = mahotas.gaussian_filter(img, 15)
  
# setting threshold value
gaussian = (gaussian > gaussian.mean())
  
# creating a labelled image
labelled, n_nucleus = mahotas.label(gaussian)
   
print("Labelled Image")
# showing the gaussian filter
imshow(labelled)
show()
  
# getting perimeters
relabeled = mahotas.labelled.bwperim(labelled, 8)
 
 
# showing the image
print("Perimeters Image")
imshow(relabelled)
show()