Monday, February 27, 2006


SIFT(Scale Invariant Feature Transform)

Distinctive image features from scale-invariant keypoints. David G.
Lowe, International Journal of Computer Vision, 60, 2 (2004), pp.

  1. Enforce invariance to scale: Compute Gaussian difference max, for
    may different scales; non-maximum suppression, find local maxima:
    keypoint candidates
  2. Localizable corner: For each maximum fit quadratic function.
    Compute center with sub-pixel accuracy by setting first derivative to
  3. Eliminate edges: Compute ratio of eigenvalues, drop keypoints for which this ratio is larger than a threshold.
  4. Enforce invariance to orientation: Compute orientation, to achieve
    scale invariance, by finding the strongest second derivative direction
    in the smoothed image (possibly multiple orientations). Rotate patch so
    that orientation points up.
  5. Compute feature signature: Compute a “gradient
    histogram” of the local image region in a 4×4 pixel region.
    Do this for 4×4 regions of that size. Orient so that largest
    gradient points up (possibly multiple solutions). Result: feature
    vector with 128 values (15 fields, 8 gradients).
  6. Enforce invariance to illumination change and camera saturation:
    Normalize to unit length to increase invariance to illumination. Then
    threshold all gradients, to become invariant to camera saturation.
    (from st course)

Codes are in paper author’s website.

No comments:

Post a Comment