In this article, we will see how we can find the solidity and the equivalent diameter of an object present in an image with help of Python OpenCV.
Function to Find Solidity
The solidity of an image is the measurement of the overall concavity of a particle. We can define the solidity of an object as the ratio of the contour area to its convex hull area. The Contour area and convex hull area should be determined first in order to compute the solidity.
Python3
# function to find Solidity def find_solidity(count): contourArea = cv2.contourArea(count) convexHull = cv2.convexHull(count) contour_hull_area = cv2.contourArea(convexHull) solidity = float(contourArea)/contour_hull_area return solidity |
Function to Find Equivalent Diameter
Also, the diameter of the circle whose area is equal to the contour area is known as the Equivalent Diameter. The Contour is an outline representing or bounding the shape or form of something.
Python3
# function to calculate the equivalent diameter def find_equi_diameter(count): area = cv2.contourArea(count) equi_diameter = np.sqrt(4*area/np.pi) return equi_diameter |
Steps to find the Solidity and the Equivalent Diameter:
- First, we need to import python’s OpenCV library and NumPy library.
- Use the function cv2.imread() to read the desired image.
- Create a binary image by applying thresholding on the grayscale image.
- Use the cv2.findContours() function to find the contours in the image.
- Compute the Solidity and the Equivalent Diameter for that we will priorly calculate the contour area and convex hull area.
- Finally, print the Solidity and the Equivalent Diameter.
Solidity and Equivalent Diameter of an Image with Single Object
We will determine the solidity and equivalent diameter of a single object in the picture using below Python program. The solidity and equivalent diameter values for the item will be printed on the console.
Python3
# import required libraries import cv2 import numpy as np # read the desired image # Give Path to the image img = cv2.imread(r"C:\Users\siddh\Downloads\star2.png") # convert the image to grayscale image grayScaleImg = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) # apply thresholding to convert # grayscale image to the binary image ret, thresh = cv2.threshold(grayScaleImg, 40, 255, 0) # find the contours contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE) print(f"{len(contours)} objects detected") # select first contour count = contours[0] # find the solidity for this contour Solidity = find_solidity(count) Solidity = round(Solidity, 2) # find the equivalent diameter for this contour equi_diameter = find_equi_diameter(count) equi_diameter = round(equi_diameter, 2) print("Solidity - ", Solidity) print("Equivalent Diameter - ", equi_diameter) |
Input Image:
star.png
Output:
1 objects detected Solidity - 0.48 Equivalent Diameter - 511.62
Solidity and Equivalent Diameter of an Image with Multiple Objects
We will determine the solidity and equivalent diameter of multiple objects in the picture using below Python program. The solidity and equivalent diameter values for the item will be printed on the console.
Python3
import cv2 import numpy as np # read the desired image # Give Path to the image img = cv2.imread(r"C:\Users\siddh\Downloads\multshapes2.png") # convert the image to grayscale image gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) # apply thresholding to convert grayscale image to the binary image # and find the contours ret, thresh = cv2.threshold(gray, 100, 255, 0) contours, hierarchy = cv2.findContours(thresh, 1, 2) print("Number of objects detected:", len(contours)) |
Now we will iteratively find the solidity and the equivalent diameter for each of the objects which are detected in the image.
Python3
# iterate over the list 'contours' to get # solidity and Equivalent Diameter of each object for i, cnt in enumerate(contours): Solidity = find_solidity(cnt) Solidity = round(Solidity, 2) equi_diameter = find_equi_diameter(cnt) equi_diameter = round(equi_diameter, 2) print(f"Solidity of object {i+1}: ", Solidity) print(f"Equivalent Diameter of object {i+1}: ", equi_diameter) |
input Image:
multiple_shapes.png
Output:
Number of objects detected: 3 Solidity of object 1: 1.0 Equivalent Diameter of object 1: 90.93 Solidity of object 2: 0.98 Equivalent Diameter of object 2: 73.14 Solidity of object 3: 0.99 Equivalent Diameter of object 3: 93.43
