Why segmentation labels every pixel in Computer Vision - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a segmentation mask where each pixel is labeled.

Computer Vision

segmentation_mask = [1](image_array, lambda pixel: pixel > 128)

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

Amap

Bapply

Cfilter

Dreduce

Attempts:

3 left

💡 Hint

Common Mistakes

Using filter instead of map which would remove pixels instead of labeling them.

The map function applies a given function to every element (pixel) in the image array, labeling each pixel accordingly.

2fill in blank

medium

Complete the code to assign a label to each pixel based on its color intensity.

Computer Vision

labels = [[[1](pixel) for pixel in row] for row in image]

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

Alen

Bmax

Csum

Dintensity_label

Attempts:

3 left

💡 Hint

Common Mistakes

Using sum or max which do not assign labels but compute values.

The function intensity_label assigns a label to each pixel based on its intensity, which is essential for segmentation.

3fill in blank

hard

Fix the error in the segmentation code by filling the blank correctly.

Computer Vision

for y in range(height):
    for x in range(width):
        segmentation_map[y][x] = [1](image[y][x])

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

Alabel_pixel

Bpixel_label

ClabelPixels

DsegmentPixel

Attempts:

3 left

💡 Hint

Common Mistakes

Using undefined or incorrectly named functions causing runtime errors.

The function label_pixel correctly labels each pixel for segmentation. The other options are invalid or undefined.

4fill in blank

hard

Fill both blanks to create a dictionary mapping pixel coordinates to labels.

Computer Vision

pixel_labels = {(x, y): [1] for x in range(width) for y in range(height) if [2]

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

Alabel_pixel(image[y][x])

Bx > 0

Cy > 0

Dx < width

Attempts:

3 left

💡 Hint

Common Mistakes

Using conditions on x instead of y, or missing the function call in the first blank.

The first blank uses label_pixel(image[y][x]) to assign labels. The second blank uses y > 0 to filter rows starting from 1.

5fill in blank

hard

Fill all three blanks to create a segmentation mask with labels for pixels above a threshold.

Computer Vision

segmentation_mask = [1]([2]: [3] for [2] in range(len(pixels)) if pixels[[2]] > threshold)

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

Adict

Bpixel

Cpixel_label(pixels[pixel])

Dlist

Attempts:

3 left

💡 Hint

Common Mistakes

Using list instead of dict, or missing the function call for labeling.

The code builds a dictionary (dict) where each pixel is mapped to its label using pixel_label(pixels[pixel]) if its value is above the threshold.