This document contains answers to questions about computer vision tasks. It shows code to open, display, convert to grayscale, check dimensions, extract channels of an image. It also shows code to extract pixels, create a new image by sampling pixels, flip an image vertically, and create a histogram.
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0 ratings0% found this document useful (0 votes)
43 views
Computer Vision Assignment
This document contains answers to questions about computer vision tasks. It shows code to open, display, convert to grayscale, check dimensions, extract channels of an image. It also shows code to extract pixels, create a new image by sampling pixels, flip an image vertically, and create a histogram.
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 7
Computer vision assignment
Submitted by – Yash Chauhan
Roll No. – 2020UCO1657 Branch – COE 3 Q1. Read an image into a variable Ans. from PIL import Image # Open an image file img = Image.open("image.jpg") # Access the pixel data pixels = img.load()
Q2. Display that image
Ans. from PIL import Image import matplotlib.pyplot as plt # Open an image file img = Image.open("image.jpg") # Display the image plt.imshow(img) plt.show() This code uses the Image.open() function from the Pillow library to open an image file and store it in the img variable. Then, it uses the plt.imshow() function from the Matplotlib library to display the image stored in the img variable. Finally, the plt.show() function is used to show the plot.
Q3. Convert an image into a gray scale image.
Ans. from PIL import Image # Open an image file img = Image.open("image.jpg").convert('L') # Save the grayscale image img.save("gray_image.jpg") Q4. Check the height and width of that image. Ans. import cv2 # Load the image img = cv2.imread("image.jpg") # Get the image size height, width, channels = img.shape # Print the size print("Width:", width) print("Height:", height) Q5. Extract the RGB channels of a given color image Ans. import cv2 # Load the image img = cv2.imread("image.jpg") # Split the image into its RGB channels r, g, b = cv2.split(img) # Display the channels cv2.imshow("Red", r) cv2.imshow("Green", g) cv2.imshow("Blue", b) # Wait for key press and then close the windows cv2.waitKey(0) cv2.destroyAllWindows()
Q6. To extract given 100 pixels from a gray scale image
Ans. import cv2 # Load the image img = cv2.imread("image.jpg", cv2.IMREAD_GRAYSCALE) # Get the height and width of the image height, width = img.shape # Calculate the starting and ending row and column indices start_row = height // 2 - 50 end_row = height // 2 + 50 start_col = width // 2 - 50 end_col = width // 2 + 50 # Extract the middle 100 pixels middle_100 = img[start_row:end_row, start_col:end_col] # Display the extracted pixels cv2.imshow("Middle 100 Pixels", middle_100) # Wait for key press and then close the window cv2.waitKey(0) cv2.destroyAllWindows() Q7. Create a new image with every 10th pixel horizontally and 20th pixel vertically Ans. import cv2 # Load the image img = cv2.imread("image.jpg", cv2.IMREAD_GRAYSCALE) # Get the height and width of the image height, width = img.shape # Initialize an empty image with reduced size reduced_img = np.zeros((height//20, width//10), dtype=np.uint8) # Fill the reduced image with every 10th pixel horizontally and 20th pixel vertically for row in range(0, height, 20): for col in range(0, width, 10): reduced_img[row//20, col//10] = img[row, col] # Display the reduced image cv2.imshow("Reduced Image", reduced_img) # Wait for key press and then close the window cv2.waitKey(0) cv2.destroyAllWindows() Q8. Flip the image vertically Ans. import cv2 # Load the image img = cv2.imread("image.jpg") # Flip the image vertically flipped_img = cv2.flip(img, 0) # Display the flipped image cv2.imshow("Flipped Image", flipped_img) # Wait for key press and then close the window cv2.waitKey(0) cv2.destroyAllWindows() Q9. Create a histogram graph and identify number of pixels with same intensity Ans. import cv2 import matplotlib.pyplot as plt # Load the image img = cv2.imread("image.jpg", cv2.IMREAD_GRAYSCALE) # Calculate the histogram of the image hist = cv2.calcHist([img], [0], None, [256], [0, 256]) # Plot the histogram plt.hist(img.ravel(), 256, [0, 256]) plt.xlim([0, 256]) plt.show()