Feature Detection Intro MCQ 15 Questions
Time: ~25 mins Intermediate

Feature Detection Intro MCQ

What makes a good keypoint, descriptor vectors, nearest-neighbor matching, ratio test, and geometric verification basics.

Easy: 5 Q Medium: 6 Q Hard: 4 Q
Keypoints

Locations

Descriptors

Vectors

Matching

NN / ratio

Invariance

Scale / rot

Local features

Many pipelines detect repeatable interest points, compute appearance descriptors, match across views, then estimate geometry (e.g., homography, essential matrix) with RANSAC.

Detector vs descriptor

Detectors propose (x,y,scale,orientation); descriptors encode local patch appearance for discrimination.

Vocabulary

Corners & blobs

Corners have two-direction intensity change; blobs respond to maxima of scale-space filters.

Distance metrics

L2 for float descriptors; Hamming for binary (ORB/BRIEF).

Lowe’s ratio

Reject ambiguous matches when nearest vs second-nearest distance ratio is high.

RANSAC

Fits a model while rejecting outliers in putative correspondences.

Typical flow

Detect → Describe → Match → Geometric verify

Pro tip: Repeatability under viewpoint/lighting matters more than raw corner count.