Assignment - 09

1. Implementing Dilation and Erosion:

● Write code to perform dilation and erosion operations on a noisy grayscale image using Python.

● Experiment with different structuring elements (e.g., square, disk, diamond) and compare how they affect the
output of dilation and erosion.

Ans:

import cv2

import numpy as np

import matplotlib.pyplot as plt

import urllib.request

from skimage.morphology import disk, square, diamond

# Function to download and read the image from a URL

def read_image_from_url(url):

resp = urllib.request.urlopen(url)

image_array = np.asarray(bytearray(resp.read()), dtype=np.uint8)

image = cv2.imdecode(image_array, cv2.IMREAD_GRAYSCALE) # Read as grayscale

return image

# Function to perform dilation and erosion

def dilation_erosion_operations(image_url):

# Step 1: Read the image from the URL

image = read_image_from_url(image_url)

# Step 2: Define structuring elements

structuring_elements = {

"Square": square(5),

"Disk": disk(5),

"Diamond": diamond(5)

# Step 3: Perform dilation and erosion with each structuring element

results = {}

for name, element in structuring_elements.items():

eroded = cv2.erode(image, element.astype(np.uint8))

results[name] = (dilated, eroded)

# Step 4: Visualize the results

plt.figure(figsize=(18, 12))

plt.subplot(4, 3, 1)

plt.title("Original Image")

plt.imshow(image, cmap='gray')

plt.axis('off')

idx = 2

for name, (dilated, eroded) in results.items():

plt.subplot(4, 3, idx)

plt.title(f"Dilation - {name}")

plt.imshow(dilated, cmap='gray')

plt.axis('off')

idx += 1

plt.subplot(4, 3, idx)

plt.title(f"Erosion - {name}")

plt.imshow(eroded, cmap='gray')

plt.axis('off')

idx += 1

plt.tight_layout()

plt.show()

# Example usage

image_url = "https://example.com/sample-image.jpg" # Replace with your image URL

dilation_erosion_operations(image_url)
2. Opening Operation:

● Implement the opening operation using OpenCV and logic.

● Apply the opening operation on a grayscale image using different structuring

elements such as rectangles, circles, and crosses.

● Compare the results obtained with different structuring elements.

import cv2

import numpy as np

import matplotlib.pyplot as plt

import urllib.request

from skimage.morphology import disk, square, diamond

# Function to download and read the image from a URL

def read_image_from_url(url):

resp = urllib.request.urlopen(url)

image_array = np.asarray(bytearray(resp.read()), dtype=np.uint8)

image = cv2.imdecode(image_array, cv2.IMREAD_GRAYSCALE) # Read as grayscale

return image

# Function to perform dilation and erosion

def dilation_erosion_operations(image_url):

# Step 1: Read the image from the URL

image = read_image_from_url(image_url)

# Step 2: Define structuring elements

structuring_elements = {

"Square": square(5),

"Disk": disk(5),

"Diamond": diamond(5)

# Step 3: Perform dilation and erosion with each structuring element

results = {}
 for name, element in structuring_elements.items():

dilated = cv2.dilate(image, element.astype(np.uint8))

eroded = cv2.erode(image, element.astype(np.uint8))

results[name] = (dilated, eroded)

# Step 4: Visualize the results

plt.figure(figsize=(18, 12))

plt.subplot(4, 3, 1)

plt.title("Original Image")

plt.imshow(image, cmap='gray')

plt.axis('off')

idx = 2

for name, (dilated, eroded) in results.items():

plt.subplot(4, 3, idx)

plt.title(f"Dilation - {name}")

plt.imshow(dilated, cmap='gray')

plt.axis('off')

idx += 1

plt.subplot(4, 3, idx)

plt.title(f"Erosion - {name}")

plt.imshow(eroded, cmap='gray')

plt.axis('off')

idx += 1

plt.tight_layout()

plt.show()

# Function to perform opening operation

def opening_operations(image_url):

# Step 1: Read the image from the URL

image = read_image_from_url(image_url)
 # Step 2: Define structuring elements

structuring_elements = {

"Rectangle": cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5)),

"Circle": cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5, 5)),

"Cross": cv2.getStructuringElement(cv2.MORPH_CROSS, (5, 5))

# Step 3: Perform opening with each structuring element

results = {}

for name, element in structuring_elements.items():

opened = cv2.morphologyEx(image, cv2.MORPH_OPEN, element)

results[name] = opened

# Step 4: Visualize the results

plt.figure(figsize=(12, 8))

plt.subplot(2, 2, 1)

plt.title("Original Image")

plt.imshow(image, cmap='gray')

plt.axis('off')

idx = 2

for name, opened in results.items():

plt.subplot(2, 2, idx)

plt.title(f"Opening - {name}")

plt.imshow(opened, cmap='gray')

plt.axis('off')

idx += 1

plt.tight_layout()

plt.show()

# Example usage

image_url = "https://example.com/sample-image.jpg" # Replace with your image URL

opening_operations(image_url)
3. Closing Operation:

● Implement the closing operation using OpenCV and logic.

● Apply the closing operation on a grayscale image using different structuring

elements such as rectangles, circles, and crosses.

● Compare the results obtained with different structuring elements.

ANS:

import cv2

import numpy as np

import matplotlib.pyplot as plt

import urllib.request

from skimage.morphology import disk, square, diamond

# Function to download and read the image from a URL

def read_image_from_url(url):

resp = urllib.request.urlopen(url)

image_array = np.asarray(bytearray(resp.read()), dtype=np.uint8)

image = cv2.imdecode(image_array, cv2.IMREAD_GRAYSCALE) # Read as grayscale

return image

# Function to perform dilation and erosion

def dilation_erosion_operations(image_url):

# Step 1: Read the image from the URL

image = read_image_from_url(image_url)

# Step 2: Define structuring elements

structuring_elements = {

"Square": square(5),

"Disk": disk(5),

"Diamond": diamond(5)

# Step 3: Perform dilation and erosion with each structuring element

for name, element in structuring_elements.items():

dilated = cv2.dilate(image, element.astype(np.uint8))

eroded = cv2.erode(image, element.astype(np.uint8))

results[name] = (dilated, eroded)

# Step 4: Visualize the results

plt.figure(figsize=(18, 12))

plt.subplot(4, 3, 1)

plt.title("Original Image")

plt.imshow(image, cmap='gray')

plt.axis('off')

idx = 2

for name, (dilated, eroded) in results.items():

plt.subplot(4, 3, idx)

plt.title(f"Dilation - {name}")

plt.imshow(dilated, cmap='gray')

plt.axis('off')

idx += 1

plt.subplot(4, 3, idx)

plt.title(f"Erosion - {name}")

plt.imshow(eroded, cmap='gray')

plt.axis('off')

idx += 1

plt.tight_layout()

plt.show()

# Function to perform opening operation

def opening_operations(image_url):

# Step 1: Read the image from the URL

image = read_image_from_url(image_url)
 # Step 2: Define structuring elements

structuring_elements = {

"Rectangle": cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5)),

"Circle": cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5, 5)),

"Cross": cv2.getStructuringElement(cv2.MORPH_CROSS, (5, 5))

# Step 3: Perform opening with each structuring element

results = {}

for name, element in structuring_elements.items():

opened = cv2.morphologyEx(image, cv2.MORPH_OPEN, element)

results[name] = opened

# Step 4: Visualize the results

plt.figure(figsize=(12, 8))

plt.subplot(2, 2, 1)

plt.title("Original Image")

plt.imshow(image, cmap='gray')

plt.axis('off')

idx = 2

for name, opened in results.items():

plt.subplot(2, 2, idx)

plt.title(f"Opening - {name}")

plt.imshow(opened, cmap='gray')

plt.axis('off')

idx += 1

plt.tight_layout()

plt.show()

# Function to perform closing operation

def closing_operations(image_url):
 # Step 1: Read the image from the URL

image = read_image_from_url(image_url)

# Step 2: Define structuring elements

structuring_elements = {

"Rectangle": cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5)),

"Circle": cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5, 5)),

"Cross": cv2.getStructuringElement(cv2.MORPH_CROSS, (5, 5))

# Step 3: Perform closing with each structuring element

results = {}

for name, element in structuring_elements.items():

closed = cv2.morphologyEx(image, cv2.MORPH_CLOSE, element)

results[name] = closed

# Step 4: Visualize the results

plt.figure(figsize=(12, 8))

plt.subplot(2, 2, 1)

plt.title("Original Image")

plt.imshow(image, cmap='gray')

plt.axis('off')

idx = 2

for name, closed in results.items():

plt.subplot(2, 2, idx)

plt.title(f"Closing - {name}")

plt.imshow(closed, cmap='gray')

plt.axis('off')

idx += 1

plt.tight_layout()

plt.show()

# Example usage

image_url = "https://example.com/sample-image.jpg" # Replace with your image URL

4. Morphological Gradient:

● Implement the morphological gradient operation using OpenCV and logic.

● Apply the morphological gradient operation on a grayscale image using different structuring elements such as
rectangles, circles, and crosses.

● Visualize and analyze the differences in results obtained with different structuring elements.

ANS:

import cv2

import numpy as np

import matplotlib.pyplot as plt

import urllib.request

from skimage.morphology import disk, square, diamond

# Function to download and read the image from a URL

def read_image_from_url(url):

resp = urllib.request.urlopen(url)

image_array = np.asarray(bytearray(resp.read()), dtype=np.uint8)

image = cv2.imdecode(image_array, cv2.IMREAD_GRAYSCALE) # Read as grayscale

return image

# Function to perform dilation and erosion

def dilation_erosion_operations(image_url):

# Step 1: Read the image from the URL

image = read_image_from_url(image_url)

# Step 2: Define structuring elements

structuring_elements = {

"Square": square(5),

"Disk": disk(5),

"Diamond": diamond(5)

# Step 3: Perform dilation and erosion with each structuring element

results = {}
 for name, element in structuring_elements.items():

dilated = cv2.dilate(image, element.astype(np.uint8))

eroded = cv2.erode(image, element.astype(np.uint8))

results[name] = (dilated, eroded)

# Step 4: Visualize the results

plt.figure(figsize=(18, 12))

plt.subplot(4, 3, 1)

plt.title("Original Image")

plt.imshow(image, cmap='gray')

plt.axis('off')

idx = 2

for name, (dilated, eroded) in results.items():

plt.subplot(4, 3, idx)

plt.title(f"Dilation - {name}")

plt.imshow(dilated, cmap='gray')

plt.axis('off')

idx += 1

plt.subplot(4, 3, idx)

plt.title(f"Erosion - {name}")

plt.imshow(eroded, cmap='gray')

plt.axis('off')

idx += 1

plt.tight_layout()

plt.show()

# Function to perform opening operation

def opening_operations(image_url):

# Step 1: Read the image from the URL

image = read_image_from_url(image_url)
 # Step 2: Define structuring elements

structuring_elements = {

"Rectangle": cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5)),

"Circle": cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5, 5)),

"Cross": cv2.getStructuringElement(cv2.MORPH_CROSS, (5, 5))

# Step 3: Perform opening with each structuring element

results = {}

for name, element in structuring_elements.items():

opened = cv2.morphologyEx(image, cv2.MORPH_OPEN, element)

results[name] = opened

# Step 4: Visualize the results

plt.figure(figsize=(12, 8))

plt.subplot(2, 2, 1)

plt.title("Original Image")

plt.imshow(image, cmap='gray')

plt.axis('off')

idx = 2

for name, opened in results.items():

plt.subplot(2, 2, idx)

plt.title(f"Opening - {name}")

plt.imshow(opened, cmap='gray')

plt.axis('off')

idx += 1

plt.tight_layout()

plt.show()

# Function to perform closing operation

def closing_operations(image_url):

# Step 1: Read the image from the URL

image = read_image_from_url(image_url)
 # Step 2: Define structuring elements

structuring_elements = {

"Rectangle": cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5)),

"Circle": cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5, 5)),

"Cross": cv2.getStructuringElement(cv2.MORPH_CROSS, (5, 5))

# Step 3: Perform closing with each structuring element

results = {}

for name, element in structuring_elements.items():

closed = cv2.morphologyEx(image, cv2.MORPH_CLOSE, element)

results[name] = closed

# Step 4: Visualize the results

plt.figure(figsize=(12, 8))

plt.subplot(2, 2, 1)

plt.title("Original Image")

plt.imshow(image, cmap='gray')

plt.axis('off')

idx = 2

for name, closed in results.items():

plt.subplot(2, 2, idx)

plt.title(f"Closing - {name}")

plt.imshow(closed, cmap='gray')

plt.axis('off')

idx += 1

plt.tight_layout()

plt.show()

# Function to perform morphological gradient operation

def morphological_gradient_operations(image_url):

# Step 1: Read the image from the URL

image = read_image_from_url(image_url)

# Step 2: Define structuring elements

structuring_elements = {

"Rectangle": cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5)),

"Circle": cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5, 5)),

# Step 3: Perform morphological gradient with each structuring element

results = {}

for name, element in structuring_elements.items():

gradient = cv2.morphologyEx(image, cv2.MORPH_GRADIENT, element)

results[name] = gradient

# Step 4: Visualize the results

plt.figure(figsize=(12, 8))

plt.subplot(2, 2, 1)

plt.title("Original Image")

plt.imshow(image, cmap='gray')

plt.axis('off')

idx = 2

for name, gradient in results.items():

plt.subplot(2, 2, idx)

plt.title(f"Gradient - {name}")

plt.imshow(gradient, cmap='gray')

plt.axis('off')

idx += 1

plt.tight_layout()

plt.show()

# Example usage

image_url = "https://example.com/sample-image.jpg" # Replace with your image URL

morphological_gradient_operations(image_url)
5. Top Hat Operation:

● Implement the top hat operation using OpenCV and logic.

● Apply the top hat operation on a grayscale image using different structuring elements such as rectangles, circles,
and crosses.

● Examine the output images and discuss the effects of different structuring elements on the results.

import cv2

import numpy as np

import matplotlib.pyplot as plt

import urllib.request

from skimage.morphology import disk, square, diamond

# Function to download and read the image from a URL

def read_image_from_url(url):

resp = urllib.request.urlopen(url)

image_array = np.asarray(bytearray(resp.read()), dtype=np.uint8)

image = cv2.imdecode(image_array, cv2.IMREAD_GRAYSCALE) # Read as grayscale

return image

# Function to perform dilation and erosion

def dilation_erosion_operations(image_url):

# Step 1: Read the image from the URL

image = read_image_from_url(image_url)

# Step 2: Define structuring elements

structuring_elements = {

"Square": square(5),

"Disk": disk(5),

"Diamond": diamond(5)

# Step 3: Perform dilation and erosion with each structuring element

results = {}
 for name, element in structuring_elements.items():

dilated = cv2.dilate(image, element.astype(np.uint8))

eroded = cv2.erode(image, element.astype(np.uint8))

results[name] = (dilated, eroded)

# Step 4: Visualize the results

plt.figure(figsize=(18, 12))

plt.subplot(4, 3, 1)

plt.title("Original Image")

plt.imshow(image, cmap='gray')

plt.axis('off')

idx = 2

for name, (dilated, eroded) in results.items():

plt.subplot(4, 3, idx)

plt.title(f"Dilation - {name}")

plt.imshow(dilated, cmap='gray')

plt.axis('off')

idx += 1

plt.subplot(4, 3, idx)

plt.title(f"Erosion - {name}")

plt.imshow(eroded, cmap='gray')

plt.axis('off')

idx += 1

plt.tight_layout()

plt.show()

# Function to perform opening operation

def opening_operations(image_url):

# Step 1: Read the image from the URL

image = read_image_from_url(image_url)
 # Step 2: Define structuring elements

structuring_elements = {

"Rectangle": cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5)),

"Circle": cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5, 5)),

"Cross": cv2.getStructuringElement(cv2.MORPH_CROSS, (5, 5))

# Step 3: Perform opening with each structuring element

results = {}

for name, element in structuring_elements.items():

opened = cv2.morphologyEx(image, cv2.MORPH_OPEN, element)

results[name] = opened

# Step 4: Visualize the results

plt.figure(figsize=(12, 8))

plt.subplot(2, 2, 1)

plt.title("Original Image")

plt.imshow(image, cmap='gray')

plt.axis('off')

idx = 2

for name, opened in results.items():

plt.subplot(2, 2, idx)

plt.title(f"Opening - {name}")

plt.imshow(opened, cmap='gray')

plt.axis('off')

idx += 1

plt.tight_layout()

plt.show()

# Function to perform closing operation

def closing_operations(image_url):

# Step 1: Read the image from the URL

# Step 2: Define structuring elements

structuring_elements = {

"Rectangle": cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5)),

"Circle": cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5, 5)),

"Cross": cv2.getStructuringElement(cv2.MORPH_CROSS, (5, 5))

# Step 3: Perform closing with each structuring element

results = {}

for name, element in structuring_elements.items():

closed = cv2.morphologyEx(image, cv2.MORPH_CLOSE, element)

results[name] = closed

# Step 4: Visualize the results

plt.figure(figsize=(12, 8))

plt.subplot(2, 2, 1)

plt.title("Original Image")

plt.imshow(image, cmap='gray')

plt.axis('off')

idx = 2

for name, closed in results.items():

plt.subplot(2, 2, idx)

plt.title(f"Closing - {name}")

plt.imshow(closed, cmap='gray')

plt.axis('off')

idx += 1

plt.tight_layout()

plt.show()

# Function to perform morphological gradient operation

# Step 1: Read the image from the URL

image = read_image_from_url(image_url)

# Step 2: Define structuring elements

structuring_elements = {

"Rectangle": cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5)),

"Circle": cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5, 5)),

"Cross": cv2.getStructuringElement(cv2.MORPH_CROSS, (5, 5))

# Step 3: Perform morphological gradient with each structuring element

results = {}

for name, element in structuring_elements.items():

gradient = cv2.morphologyEx(image, cv2.MORPH_GRADIENT, element)

results[name] = gradient

# Step 4: Visualize the results

plt.figure(figsize=(12, 8))

plt.subplot(2, 2, 1)

plt.title("Original Image")

plt.imshow(image, cmap='gray')

plt.axis('off')

idx = 2

for name, gradient in results.items():

plt.subplot(2, 2, idx)

plt.title(f"Gradient - {name}")

plt.imshow(gradient, cmap='gray')

plt.axis('off')

idx += 1

plt.tight_layout()

plt.show()
# Function to perform top hat operation

def top_hat_operations(image_url):

# Step 1: Read the image from the URL

image = read_image_from_url(image_url)

# Step 2: Define structuring elements

structuring_elements = {

"Rectangle": cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5)),

"Circle": cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5, 5)),

"Cross": cv2.getStructuringElement(cv2.MORPH_CROSS, (5, 5))

# Step 3: Perform top hat operation with each structuring element

results = {}

for name, element in structuring_elements.items():

top_hat = cv2.morphologyEx(image, cv2.MORPH_TOPHAT, element)

results[name] = top_hat

# Step 4: Visualize the results

plt.figure(figsize=(12, 8))

plt.subplot(2, 2, 1)

plt.title("Original Image")

plt.imshow(image, cmap='gray')

plt.axis('off')

idx = 2

for name, top_hat in results.items():

plt.subplot(2, 2, idx)

plt.title(f"Top Hat - {name}")

plt.imshow(top_hat, cmap='gray')

plt.axis('off')

idx += 1

plt.tight_layout()

plt.show()

# Example usage

image_url = "https://example.com/sample-image.jpg" # Replace with your image URL

6. Black Hat Operation:

● Implement the black hat operation using OpenCV and logic.

● Apply the black hat operation on a grayscale image using different structuring

elements such as rectangles, circles, and crosses.

import cv2

import numpy as np

import requests

from io import BytesIO

import matplotlib.pyplot as plt

# Function to download and load an image from URL

def load_image_from_url(url):

response = requests.get(url)

img_array = np.array(bytearray(response.content), dtype=np.uint8)

image = cv2.imdecode(img_array, -1) # Decode the image to grayscale

return image

# Image URL (replace this with your image URL)

image_url = 'https://encrypted-
tbn0.gstatic.com/images?q=tbn:ANd9GcQ3VeYXSb6lCYDJJwi2XFj7Mtn3dmR9QdHafA&s'

# Load the grayscale image

image = load_image_from_url(image_url)

# Check if the image was loaded properly

if image is None:

print("Error loading image!")

else:

# Define structuring elements

kernel_rect = cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5)) # Rectangle

kernel_circle = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5, 5)) # Circle

kernel_cross = cv2.getStructuringElement(cv2.MORPH_CROSS, (5, 5)) # Cross

black_hat_rect = cv2.dilate(image, kernel_rect) - image

black_hat_circle = cv2.dilate(image, kernel_circle) - image

black_hat_cross = cv2.dilate(image, kernel_cross) - image

# Plot the original image and the results

plt.figure(figsize=(10, 10))

plt.subplot(2, 2, 1)

plt.imshow(image, cmap='gray')

plt.title('Original Image')

plt.axis('off')

plt.subplot(2, 2, 2)

plt.imshow(black_hat_rect, cmap='gray')

plt.title('Black Hat (Rectangle)')

plt.axis('off')

plt.subplot(2, 2, 3)

plt.imshow(black_hat_circle, cmap='gray')

plt.title('Black Hat (Circle)')

plt.axis('off')

plt.subplot(2, 2, 4)

plt.imshow(black_hat_cross, cmap='gray')

plt.title('Black Hat (Cross)')

plt.axis('off')

plt.tight_layout()

plt.show()