In this article we will see how we can get the image roundness feature in mahotas. Roundness is dominated by the shape’s gross features rather than the definition of its edges and corners, or the surface roughness of a manufactured object. A smooth ellipse can have low roundness, if its eccentricity is large
For this tutorial we will use ‘lena’ image, below is the command to load the lena image
mahotas.demos.load('lena')
Below is the lena image
In order to do this we will use mahotas.features.roundness method
Syntax : mahotas.features.roundness(img)
Argument : It takes image object as argument
Return : It returns float value
Note : Input image should be filtered or should be 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]
Below is the implementation
# importing required libraries import mahotas
import mahotas.demos
from pylab import gray, imshow, show
import numpy as np
import matplotlib.pyplot as plt
# loading image img = mahotas.demos.load( 'lena' )
# filtering image img = img. max ( 2 )
print ( "Image" )
# showing image imshow(img) show() # computing roundness in image value = mahotas.features.roundness(img)
# printing value print ( "Roundness : " + str (value))
|
Output :
Image
Roundness : 0.0
Another example
# importing required libraries import mahotas
import numpy as np
from pylab import gray, imshow, show
import os
import matplotlib.pyplot as plt
# loading image img = mahotas.imread( 'dog_image.png' )
# filtering image img = img[:, :, 0 ]
print ( "Image" )
# showing image imshow(img) show() # computing roundness in image value = mahotas.features.roundness(img)
# printing value print ( "Roundness : " + str (value))
|
Output :
Image
Roundness : 0.04297201733896709