Related Articles

Related Articles

Mahotas – Filtering Labels
  • Last Updated : 21 Jun, 2020

In this article we will see how we can filter the labels of the labelled image in mahotas. Filtering label is similar to implementing the relabeling feature but the difference is in filtering we will remove i.e filter the labels at the time of calling the filtering method and filtering will give us new labeled image and number of labels. We use mahotas.label method to label the image

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

mhotas.demos.nuclear_image()

Below is the nuclear_image

Labeled 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.filter_labeled method



Syntax : mahotas.label.filter_labeled(label_image, filter1, filter2)

Argument : It takes labeled image object and filters as argument

Return : It returns the labelled image and integer i.e number of labels

Note : Filters can be border label filter, maximum size anything.

Example 1:

filter_none

edit
close

play_arrow

link
brightness_4
code

# 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 labeled image
labeled, n_nucleus = mahotas.label(f)
  
# printing number of labels
print("Count : " + str(n_nucleus))
  
# showing the labeleed image
print("Labelled Image")
imshow(labeled)
show()
  
  
# filtering the label image
# adding border filter
relabeled, n_left = mahotas.labeled.filter_labeled(labeled, remove_bordering = True)
  
# showing number of labels
print("Count : " + str(n_left))
  
# showing the image
print("No border Label")
imshow(relabeled)
show()

chevron_right


Output :

Example 2:

filter_none

edit
close

play_arrow

link
brightness_4
code

# 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 labeled image
labeled, n_nucleus = mahotas.label(f)
  
# printing number of labels
print("Count : " + str(n_nucleus))
  
# showing the labeleed image
print("Labelled Image")
imshow(labeled)
show()
  
  
# filtering the label image
# adding max size filter
relabeled, n_left = mahotas.labeled.filter_labeled(labeled, max_size = 7000)
  
# showing number of labels
print("Count : " + str(n_left))
  
# showing the image
print("Max size 7000 Label")
imshow(relabeled)
show()

chevron_right


Output :

Attention geek! Strengthen your foundations with the Python Programming Foundation Course and learn the basics.

To begin with, your interview preparations Enhance your Data Structures concepts with the Python DS Course.




My Personal Notes arrow_drop_up
Recommended Articles
Page :