Mahotas – Labelled Image from the Normal Image

0 0 1 minute read

In this article we will see how we can create a labelled image from the normal image 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

Labelled images are integer images where the values correspond to different regions. I.e., region 1 is all of the pixels which have value 1, region two is the pixels with value 2, and so on
In order to do this we will use mahotas.label method

Syntax : mahotas.label(image)
Argument : It takes loaded image object as argument
Return : It returns the labelled image and the integer i.e number of labels

Note : The input of the label should be the filtered image object and it should have the threshold and it is preferred that image should have gaussian filter for removing sharper edges.
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]
 
# show the image
print("Image")
imshow(f)
show()
 
# 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()

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]
    
print("Image")
# showing the image
imshow(img)
show()
  
# setting gaussian filter
gaussian = mahotas.gaussian_filter(img, 15)
 
# setting threshold value
gaussian = (gaussian > gaussian.mean())
 
# creating a labelled image
labelled, n_nucleus = mh.label(gaussian)
  
print("Labelled Image")
# showing the gaussian filter
imshow(labelled)
show()