Which candidate points survive
Every point that stands out from its neighbours in position and in scale on a harbour photo, coloured by what happens to it: kept, too weak, too much like an edge, or dropped because its position could not be pinned down. The two sliders are the two thresholds SIFT uses.
Try this
Raise the contrast threshold and watch the faint water and sky points go first. Then lower the edge ratio and see which points along the quay edges drop out.
Where this lab comes from
How SIFT Finds Keypoints: Extrema, Refinement, OrientationHow SIFT turns a stack of blurred photos into a short list of points it can find again: every point that beats its 26 neighbours, a sub-pixel fit, a contrast test, an edge test and a direction for each survivor. Built from scratch on a photo of Barcelona harbour, where 7,053 candidates become 2,896 points and 3,510 keypoints, and checked against OpenCV keypoint for keypoint.
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.