Scribd
Upload
5 views

Image segmentation

Uploaded by

yesh89012
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
5 views

Image segmentation

Uploaded by

yesh89012
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Image segmentation (Point Line Edges)

import cv2
import numpy as np
import matplotlib.pyplot as plt

# Read the input image


image_path = 'cat.jpg' # Path to the image (update this with the actual path)
image = cv2.imread(image_path) # Reads the image from the given path using OpenCV

# Convert to grayscale
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) # Converts the image to grayscale (OpenCV uses
BGR by default)

# Part 1: Segmentation (using Thresholding)


# Thresholding is used to segment an image into two regions: one above a threshold and the other
below

# Apply a simple binary threshold


# The threshold value is set to 127, where pixels greater than 127 will be set to 255 (white),
# and those less than 127 will be set to 0 (black).
_, thresholded_image = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY)

# Display the segmented image


plt.figure(figsize=(10, 5)) # Set the size of the plot

# Plot the original image on the left side of the subplot


plt.subplot(1, 2, 1) # 1 row, 2 columns, this is the first subplot
plt.title('Original Image') # Set the title for the original image
plt.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB)) # Convert BGR to RGB for correct color
display with matplotlib
plt.axis('off') # Turn off axis labels

# Plot the segmented image (thresholded image) on the right side


plt.subplot(1, 2, 2) # 1 row, 2 columns, this is the second subplot
plt.title('Segmented Image (Thresholding)') # Title for the thresholded image
plt.imshow(thresholded_image, cmap='gray') # Display the binary image in grayscale
plt.axis('off') # Turn off axis labels

# Show the plots


plt.show()

# Part 2: Point-Line Edges Detection (using Canny edge detection)


# Canny edge detection is used to detect edges in an image by identifying areas with rapid intensity
changes

# Apply the Canny edge detector


# The first parameter is the image, and the second and third are the low and high thresholds for edge
detection.
edges = cv2.Canny(gray, 100, 200) # Detect edges in the grayscale image

# Display the edges detected by Canny


plt.figure(figsize=(10, 5)) # Set the size of the plot
# Plot the original image again on the left side of the subplot
plt.subplot(1, 2, 1)
plt.title('Original Image') # Title for the original image
plt.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB)) # Display the original image in RGB format
plt.axis('off') # Turn off axis labels

# Plot the detected edges on the right side


plt.subplot(1, 2, 2)
plt.title('Detected Edges (Canny)') # Title for the edges image
plt.imshow(edges, cmap='gray') # Display the edge-detected image in grayscale
plt.axis('off') # Turn off axis labels

# Show the plots


plt.show()

# Optionally: Extracting points along the edges


# The edges array contains the results of the Canny edge detection, with non-zero values indicating
edges.

# np.column_stack(np.where(edges > 0)) extracts the coordinates (i.e., x, y points) of all non-zero
pixels (edges).
edge_points = np.column_stack(np.where(edges > 0))

# Displaying the number of edge points detected


print(f'Number of points detected on the edge: {len(edge_points)}') # Print the number of edge
points found

#out Put

You might also like