SIFT features in Computer Vision - Cheat Sheet & Quick Revision

Recall & Review

beginner

What does SIFT stand for in computer vision?

SIFT stands for Scale-Invariant Feature Transform. It is a method to detect and describe local features in images.

beginner

Why is SIFT called 'scale-invariant'?

Because SIFT features can be detected and matched even if the image is resized or zoomed in/out, making them robust to scale changes.

intermediate

What are the main steps in the SIFT algorithm?

1. Detect scale-space extrema using Difference of Gaussians (DoG).
2. Localize keypoints and filter out unstable ones.
3. Assign orientation to each keypoint.
4. Create a descriptor based on local image gradients around the keypoint.

intermediate

How does SIFT handle rotation invariance?

SIFT assigns a dominant orientation to each keypoint based on local gradients, so the descriptor is computed relative to this orientation, making it rotation invariant.

beginner

What is a SIFT descriptor and what is it used for?

A SIFT descriptor is a vector that describes the local image gradients around a keypoint. It is used to match keypoints between different images for tasks like object recognition or image stitching.

What is the first step in the SIFT algorithm?

A Match keypoints between images

B Assign orientation to keypoints

C Create descriptors

D Detect scale-space extrema using Difference of Gaussians

The first step is to detect potential keypoints by finding extrema in the scale-space using Difference of Gaussians.

Why is SIFT robust to changes in image scale?

A It uses color histograms

B It detects features at multiple scales

C It only works on fixed-size images

D It ignores image brightness

SIFT detects features at multiple scales by building a scale-space, making it robust to resizing.

How does SIFT achieve rotation invariance?

A By ignoring orientation

B By resizing the image

C By assigning a dominant orientation to each keypoint

D By using color information

SIFT assigns a dominant orientation to each keypoint and computes descriptors relative to that orientation.

What type of descriptor does SIFT use?

A Histogram of gradients

B Binary descriptor

C Raw pixel values

D Edge detection map

SIFT uses histograms of local image gradients to form its descriptor.

Which of these is NOT a property of SIFT features?

A Color invariance

B Rotation invariance

C Scale invariance

D Robustness to illumination changes

SIFT features are not specifically color invariant; they focus on grayscale gradients.

Explain the main steps of the SIFT algorithm and why each step is important.

Think about how SIFT finds stable points and describes them to match across images.

Describe how SIFT features help in matching objects between two images taken from different distances and angles.

Consider what changes in the images and how SIFT handles them.

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