In this article we will see how we can get the linear binary patterns of image in mahotas. Local binary patterns is a type of visual descriptor used for classification in computer vision. LBP is the particular case of the Texture Spectrum model proposed in 1990. LBP was first described in 1994. 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
In order to do this we will use mahotas.features.lbp method
Syntax : mahotas.features.lbp(image, radius, points)
Argument : It takes image object and two integers as argument
Return : It returns 1-D numpy ndarray i.e histogram feature
Note : The input of the this should be the filtered image or loaded as grey
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 various librariesimport mahotasimport mahotas.demosimport mahotas as mhimport numpy as npfrom pylab import imshow, showimport matplotlib.pyplot as plt# loading nuclear imagenuclear = mahotas.demos.nuclear_image()# filtering imagenuclear = nuclear[:, :, 0]# adding gaussian filternuclear = mahotas.gaussian_filter(nuclear, 4)# setting thresholdthreshed = (nuclear > nuclear.mean())# making is labelled imagelabeled, n = mahotas.label(threshed)# showing imageprint("Labelled Image")imshow(labelled)show()# Computing Linear Binary Patternsvalue = mahotas.features.lbp(labelled, 200, 5)# showing histographplt.hist(value) |
Output :
Example 2 :
Python3
# importing required librariesimport numpy as npimport mahotasfrom pylab import imshow, showimport matplotlib.pyplot as plt # loading imageimg = mahotas.imread('dog_image.png') # filtering the imageimg = img[:, :, 0] # setting gaussian filtergaussian = mahotas.gaussian_filter(img, 15) # setting threshold valuegaussian = (gaussian > gaussian.mean()) # making is labelled imagelabeled, n = mahotas.label(gaussian)# showing imageprint("Labelled Image")imshow(labelled)show()# Computing Linear Binary Patternsvalue = mahotas.features.lbp(labelled, 200, 5, ignore_zeros = False)# showing histographplt.hist(value) |
Output :
