Image thresholding (binary, adaptive, Otsu) in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to apply a simple binary threshold to the grayscale image.

Computer Vision

_, binary_img = cv2.threshold(gray_img, [1], 255, cv2.THRESH_BINARY)

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

A1

B255

C0

D127

Attempts:

3 left

💡 Hint

Common Mistakes

Using 255 as threshold makes all pixels white.

Using 0 as threshold makes all pixels white.

The threshold value for binary thresholding is typically set around 127 for 8-bit images. Pixels above 127 become white (255), below become black (0).

2fill in blank

medium

Complete the code to apply adaptive mean thresholding with a block size of 11.

Computer Vision

adaptive_img = cv2.adaptiveThreshold(gray_img, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY, [1], 2)

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

A5

B11

C3

D7

Attempts:

3 left

💡 Hint

Common Mistakes

Using even numbers for block size causes errors.

Using too small block size may cause noisy results.

The block size defines the size of the neighborhood area used to calculate the threshold for adaptive thresholding. It must be an odd number, here 11.

3fill in blank

hard

Fix the error in the code to correctly compute Otsu's threshold value.

Computer Vision

otsu_thresh_val, otsu_img = cv2.threshold(gray_img, 0, 255, [1] + cv2.THRESH_OTSU)

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

Acv2.THRESH_BINARY

Bcv2.THRESH_TRUNC

Ccv2.THRESH_TOZERO

Dcv2.THRESH_BINARY_INV

Attempts:

3 left

💡 Hint

Common Mistakes

Using non-binary threshold types with Otsu causes incorrect results.

Using THRESH_BINARY_INV changes foreground/background.

Otsu's method is combined with a binary threshold type, so cv2.THRESH_BINARY + cv2.THRESH_OTSU is correct.

4fill in blank

hard

Fill both blanks to create a dictionary with threshold types and their OpenCV constants.

Computer Vision

threshold_types = {'binary': [1], 'adaptive_mean': [2]

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

Acv2.THRESH_BINARY

Bcv2.ADAPTIVE_THRESH_MEAN_C

Ccv2.THRESH_BINARY_INV

Dcv2.ADAPTIVE_THRESH_GAUSSIAN_C

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing adaptive mean and Gaussian constants.

Using inverted binary threshold for 'binary' key.

Binary threshold uses cv2.THRESH_BINARY, adaptive mean threshold uses cv2.ADAPTIVE_THRESH_MEAN_C.

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that maps image names to their thresholded images if mean pixel value is above 100.

Computer Vision

result = {name: img for name, img in images.items() if img[1]mean() [2] [3]

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

A.

B>

C100

D==

Attempts:

3 left

💡 Hint

Common Mistakes

Using '==' instead of '>' for comparison.

Missing the '.' before mean().

The code accesses the mean method with '.', then checks if mean is greater than 100.