Find the same points again
The 300 strongest points of Harris or SIFT on a photo of Barcelona harbour. After the photo is turned and shrunk, a point is green when the detector finds it again within 1.5 px of where it should be, and red when it does not. SIFT points are drawn at their own size; Harris points have none.
Try this
Shrink the photo to half size and compare the two detectors. Then read the last line: how many SIFT matches survive the same change.
Where this lab comes from
What Makes a Good Keypoint? Repeatability, MeasuredA good keypoint is one a detector finds again in another photo of the same scene, in the same place and at the same size. Measured on a harbour photo under known turns, zooms, blur and noise: on position alone Harris corners and SIFT points come back about equally often, and which one leads depends on the tolerance; what SIFT adds is a size that follows the zoom, which takes correct matches across a 2× zoom from 1 to 294.
More in edges and features
- An edge, and its two derivatives — One row of pixels, with the first and second derivative stacked underneath.
- Canny, one stage per panel — Smoothing and the two hysteresis thresholds, on a real photo.
- Flat, edge, or corner — Drag a window over a photo; two eigenvalues deliver the verdict.