Why responsible CV prevents misuse in Computer Vision - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load an image using OpenCV.

Computer Vision

import cv2
image = cv2.[1]('photo.jpg')

Drag options to blanks, or click blank then click option'

Aimshow

Bimread

Cimwrite

Dresize

Attempts:

3 left

💡 Hint

Common Mistakes

Using imshow instead of imread

Trying to write the image before loading it

The cv2.imread function reads an image from a file, which is the first step in computer vision tasks.

2fill in blank

medium

Complete the code to convert the image to grayscale.

Computer Vision

gray_image = cv2.cvtColor(image, [1])

Drag options to blanks, or click blank then click option'

Acv2.COLOR_BGR2GRAY

Bcv2.COLOR_BGR2RGB

Ccv2.COLOR_RGB2BGR

Dcv2.COLOR_GRAY2BGR

Attempts:

3 left

💡 Hint

Common Mistakes

Using COLOR_BGR2RGB which changes color space but not to grayscale

Using COLOR_GRAY2BGR which is the opposite conversion

To convert a color image to grayscale, use cv2.COLOR_BGR2GRAY as the color conversion code.

3fill in blank

hard

Fix the error in the code to display the image correctly.

Computer Vision

cv2.[1]('Image Window', gray_image)
cv2.waitKey(0)
cv2.destroyAllWindows()

Drag options to blanks, or click blank then click option'

Aimwrite

Bimread

Cimshow

Dresize

Attempts:

3 left

💡 Hint

Common Mistakes

Using imread instead of imshow

Trying to write the image instead of displaying it

The cv2.imshow function displays an image in a window. Using imread or imwrite here would cause errors.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps image names to their sizes if width is greater than 100.

Computer Vision

image_sizes = {name: image.shape[[1]] for name, image in images.items() if image.shape[[2]] > 100}

Drag options to blanks, or click blank then click option'

A1

B0

C2

D3

Attempts:

3 left

💡 Hint

Common Mistakes

Confusing width and height indexes

Using the same index for both blanks

In OpenCV images, shape[1] is width and shape[0] is height. We want width > 100, so use shape[1] for size and shape[0] for height if needed.

5fill in blank

hard

Fill all three blanks to filter images with more than 3 channels and create a new dictionary with their names and channel counts.

Computer Vision

filtered = {name: image.shape[[1]] for name, image in images.items() if image.shape[[2]] > [3]

Drag options to blanks, or click blank then click option'

A2

B1

C3

D0

Attempts:

3 left

💡 Hint

Common Mistakes

Using height or width index instead of channels

Checking for channels < 3 instead of > 3

The third dimension (index 2) in image shape is the number of channels. We check if channels > 3 to filter images.