SIFT scale and rotation invariance
WHAT IT TESTS: how SIFT achieves invariance. OUTLINE: scale-space extrema via difference-of-Gaussians give scale invariance; a dominant gradient orientation gives rotation invariance; the descriptor is a normalized gradient histogram.
WHAT IT TESTS: understanding of each invariance mechanism. ANSWER OUTLINE: SIFT builds a scale space and detects extrema in the difference-of-Gaussians, so a feature is found at its characteristic scale (scale invariance). Each keypoint is assigned a dominant orientation from the local gradient histogram, and the descriptor is computed relative to that orientation (rotation invariance). The descriptor is a normalized histogram of gradients in a grid, adding illumination robustness.
Read the original → interview
- #sift
- #scale-space
- #difference-of-gaussians
- #feature-descriptor
- #invariance
Get five bites like this every day.
Tezvyn delivers a daily feed of 60-second tech bites with quizzes to lock in what you learn.