Why computer vision teaches machines to see - 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]('image.jpg')

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

Aimread

Bimwrite

Cimshow

Dresize

Attempts:

3 left

💡 Hint

Common Mistakes

Using imshow instead of imread will display an image, not load it.

The cv2.imread function reads an image from a file into a matrix that the computer can process.

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_RGB2BGR

Ccv2.COLOR_GRAY2BGR

Dcv2.COLOR_BGR2RGB

Attempts:

3 left

💡 Hint

Common Mistakes

Using COLOR_BGR2RGB changes color format but not to grayscale.

cv2.COLOR_BGR2GRAY converts a color image to grayscale, which simplifies the image for many computer vision tasks.

3fill in blank

hard

Fix the error in the code to detect edges using Canny.

Computer Vision

edges = cv2.Canny(image, [1], 150)

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

A'50'

B50

CNone

Dimage

Attempts:

3 left

💡 Hint

Common Mistakes

Passing a string '50' causes a type error.

The first threshold for the Canny edge detector should be a number, like 50, not a string or None.

4fill in blank

hard

Fill both blanks to create a dictionary of pixel intensities for pixels greater than 100.

Computer Vision

pixel_dict = { (x, y): image[x, y] for x in range(image.shape[[1]]) for y in range(image.shape[[2]]) if image[x, y] > 100 }

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

A0

B1

C2

D3

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up width and height indices.

In an image array, shape[0] is height (rows) and shape[1] is width (columns).

5fill in blank

hard

Fill all three blanks to create a dictionary of pixel intensities for pixels with intensity above 120 in grayscale image.

Computer Vision

bright_pixels = { ([1], [2]): gray_image[[1], [2]] for [1] in range(gray_image.shape[0]) for [2] in range(gray_image.shape[1]) if gray_image[[1], [2]] > 120 }

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

Ax

By

Cz

Di

Attempts:

3 left

💡 Hint

Common Mistakes

Using different variables inconsistently causes errors.

We use variables x and y to loop over rows and columns. The first blank is x, second is y, and the third repeats x to index the image.