SIFT features in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a SIFT detector using OpenCV.

Computer Vision

import cv2
sift = cv2.[1]()

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

ASiftDetector

BSIFT_create

CcreateSIFT

Dcreate_sift

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'createSIFT' which is not a valid OpenCV function.

Trying 'SiftDetector' which does not exist.

The correct function to create a SIFT detector in OpenCV is SIFT_create().

2fill in blank

medium

Complete the code to detect keypoints and descriptors from an image using SIFT.

Computer Vision

keypoints, descriptors = sift.[1](image, None)

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

AfindKeypoints

Bdetect

Ccompute

DdetectAndCompute

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'detect' only detects keypoints but does not compute descriptors.

Using 'compute' requires keypoints as input and does not detect them.

The method detectAndCompute() detects keypoints and computes descriptors in one step.

3fill in blank

hard

Fix the error in the code to draw keypoints on the image using OpenCV.

Computer Vision

output_image = cv2.drawKeypoints(image, keypoints, [1], flags=cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)

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

ANone

Bimage

Ckeypoints

Doutput_image

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the input image as the third argument, which causes errors.

Passing keypoints or output_image which are invalid here.

The third argument to drawKeypoints should be None to create a new output image.

4fill in blank

hard

Fill both blanks to create a dictionary of keypoint coordinates and their sizes.

Computer Vision

kp_dict = {kp.pt: kp.{{BLANK_2}} for kp in keypoints}

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

Aangle

B{kp.pt

Csize

Dresponse

Attempts:

3 left

💡 Hint

Common Mistakes

Using angle or response instead of size for the value.

Not starting the dictionary comprehension with a curly brace.

The dictionary comprehension starts with {kp.pt and uses the size attribute of keypoints.

5fill in blank

hard

Fill all three blanks to filter keypoints by their response and create a list of their coordinates.

Computer Vision

filtered_points = [kp.[1] for kp in keypoints if kp.[2] > [3]]

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

Apt

Bresponse

C0.01

Dsize

Attempts:

3 left

💡 Hint

Common Mistakes

Using size instead of response for filtering.

Using the wrong attribute for the list elements.

We want the point coordinates kp.pt for keypoints with response greater than 0.01.