SIFT features in Computer Vision - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

What is the main purpose of SIFT features in computer vision?

SIFT (Scale-Invariant Feature Transform) features are widely used in computer vision. What is their main purpose?

A To enhance image contrast and brightness for better visualization

B To perform image segmentation by dividing an image into regions

C To detect and describe local features in images that are invariant to scale and rotation

D To compress images without losing important details

💡 Hint

Think about what SIFT helps with when matching parts of images taken from different distances or angles.

SIFT features detect key points and describe them so they can be matched even if the image is scaled or rotated. This helps in tasks like object recognition and image stitching.

❓ Predict Output

intermediate

Output of SIFT keypoints detection code snippet

What will be the output of the following Python code using OpenCV's SIFT detector?

Computer Vision

import cv2
import numpy as np
img = np.zeros((100, 100), dtype=np.uint8)
sift = cv2.SIFT_create()
keypoints = sift.detect(img, None)
print(len(keypoints))

A 0

B 100

C 1

D Raises an error because image is empty

💡 Hint

Consider what happens when you detect features in a completely black image.

The image is completely black with no edges or corners, so no keypoints are detected. The output is 0.

❓ Model Choice

advanced

Choosing the best feature descriptor for scale and rotation invariance

You want to match features between images taken from different distances and angles. Which feature descriptor is best suited for this?

A Raw pixel intensity values

B Haar Cascades

C Histogram of Oriented Gradients (HOG)

D SIFT

💡 Hint

Think about which descriptor is designed to handle changes in scale and rotation.

SIFT is specifically designed to be invariant to scale and rotation, making it ideal for matching features under such changes. Haar Cascades are for object detection, HOG is for shape, and raw pixels are not invariant.

❓ Hyperparameter

advanced

Effect of changing the number of octave layers in SIFT

In SIFT, the number of octave layers controls the number of scale levels per octave. What is the effect of increasing this number?

A Fewer keypoints detected and faster computation

B More detailed scale space representation, potentially detecting more keypoints but increasing computation time

C No effect on keypoint detection or computation time

D Causes the algorithm to ignore rotation invariance

💡 Hint

Think about how more layers per octave affect the scale space and processing.

Increasing octave layers means more scale levels are analyzed, which can detect more keypoints but requires more computation.

❓ Metrics

expert

Evaluating SIFT feature matching quality

You matched SIFT features between two images and want to evaluate the quality of matches. Which metric best measures the ratio of correct matches to total matches?

A Precision

B Recall

C Mean Squared Error

D Confusion Matrix

💡 Hint

Consider the metric that tells you how many matches are actually correct out of all matches found.

Precision measures the proportion of true positive matches among all matches found, indicating match quality. Recall measures how many true matches were found out of all possible true matches. MSE and confusion matrix are not directly used here.

Practice

1. What is the main purpose of SIFT features in computer vision?

easy

A. To compress images without losing quality

B. To increase the brightness of an image

C. To find and describe important points in images for matching

D. To convert images from color to grayscale

Solution

1. Step 1: Understand SIFT's role

   SIFT detects key points in images and creates unique descriptors for them.

2. Step 2: Identify the correct purpose

   This helps match or recognize objects even if the image changes angle or lighting.

3. Final Answer:

   To find and describe important points in images for matching -> Option C

4. Quick Check:

   SIFT purpose = find and describe key points [OK]

Hint: SIFT = find special points to match images [OK]

Common Mistakes:

• Thinking SIFT changes image brightness
• Confusing SIFT with image compression
• Believing SIFT converts image colors

2. Which of the following is the correct way to create a SIFT detector using OpenCV in Python?

easy

A. sift = cv2.SIFT()

B. sift = cv2.createSIFT()

C. sift = cv2.create_sift_detector()

D. sift = cv2.SIFT_create()

Solution

1. Step 1: Recall OpenCV SIFT syntax

   OpenCV uses SIFT_create() method to create a SIFT detector.

2. Step 2: Match syntax to options

   Only sift = cv2.SIFT_create() matches the correct method name and syntax.

3. Final Answer:

   sift = cv2.SIFT_create() -> Option D

4. Quick Check:

   OpenCV SIFT creation = cv2.SIFT_create() [OK]

Hint: Remember exact method: SIFT_create() in OpenCV [OK]

Common Mistakes:

• Using wrong method names like createSIFT()
• Trying to call SIFT() directly
• Using underscores incorrectly in method names

3. What will be the output type of the following code snippet?

import cv2
img = cv2.imread('image.jpg', 0)
sift = cv2.SIFT_create()
keypoints, descriptors = sift.detectAndCompute(img, None)
print(type(keypoints), type(descriptors))

medium

A.

B.

C.

D.

Solution

1. Step 1: Understand detectAndCompute output

   detectAndCompute returns keypoints as a list of KeyPoint objects and descriptors as a numpy array.

2. Step 2: Match output types to options

   Keypoints are a list, descriptors are numpy.ndarray, matching .

3. Final Answer:

   <class 'list'> <class 'numpy.ndarray'> -> Option A

4. Quick Check:

   keypoints=list, descriptors=numpy.ndarray [OK]

Hint: Keypoints list, descriptors numpy array from detectAndCompute [OK]

Common Mistakes:

• Assuming both outputs are lists
• Thinking descriptors are tuples
• Confusing keypoints as numpy arrays

4. Identify the error in this code snippet for detecting SIFT features:

import cv2
img = cv2.imread('image.jpg')
sift = cv2.SIFT_create()
keypoints, descriptors = sift.detectAndCompute(img, None)
print(len(keypoints))

medium

A. Image should be read in grayscale mode

B. SIFT_create() is deprecated

C. detectAndCompute requires a mask argument

D. print(len(keypoints)) should be print(keypoints)

Solution

1. Step 1: Check image reading mode

   SIFT works best on grayscale images; reading in color may cause issues.

2. Step 2: Identify correct fix

   Change cv2.imread('image.jpg') to cv2.imread('image.jpg', 0) to read grayscale.

3. Final Answer:

   Image should be read in grayscale mode -> Option A

4. Quick Check:

   Image mode must be grayscale for SIFT [OK]

Hint: Always read images in grayscale for SIFT detection [OK]

Common Mistakes:

• Ignoring image color mode
• Thinking mask argument is mandatory
• Misusing print function on keypoints

5. You want to match SIFT features between two images but notice many false matches. Which approach can improve matching accuracy?

hard

A. Increase image brightness before detection

B. Use Lowe's ratio test to filter matches

C. Use only the first 10 keypoints from each image

D. Convert images to color before detecting features

Solution

1. Step 1: Understand false matches in SIFT

   False matches occur when descriptors are similar but not correct matches.

2. Step 2: Apply Lowe's ratio test

   Lowe's ratio test compares the best and second-best matches to keep only good matches, reducing false positives.

3. Final Answer:

   Use Lowe's ratio test to filter matches -> Option B

4. Quick Check:

   Filtering matches with Lowe's ratio test reduces false matches [OK]

Hint: Apply Lowe's ratio test to keep good matches only [OK]

Common Mistakes:

• Changing brightness instead of filtering matches
• Using only few keypoints arbitrarily
• Converting images to color unnecessarily