skimage.feature.match:match_descriptors

Parameters

descriptors1 : ndarray of shape (M, P)

Descriptors of size P about M keypoints in the first image.

descriptors2 : ndarray of shape (N, P)

Descriptors of size P about N keypoints in the second image.

metric : str, see `metric` in :func:`scipy.spatial.distance.cdist`, optional

The metric to compute the distance between two descriptors. The Hamming distance should be used for binary descriptors. By default the L2-norm is used for all descriptors of dtype float or double and the Hamming distance is used for binary descriptors automatically.

p : int, optional

The p-norm to apply for metric='minkowski'.

max_distance : float, optional

Maximum allowed distance between descriptors of two keypoints in separate images to be regarded as a match.

cross_check : bool, optional

If True, the matched keypoints are returned after cross checking i.e. a matched pair (keypoint1, keypoint2) is returned if keypoint2 is the best match for keypoint1 in second image and keypoint1 is the best match for keypoint2 in first image.

max_ratio : float, optional

Maximum ratio of distances between first and second closest descriptor in the second set of descriptors. This threshold is useful to filter ambiguous matches between the two descriptor sets. The choice of this value depends on the statistics of the chosen descriptor, e.g., for SIFT descriptors a value of 0.8 is usually chosen, see D.G. Lowe, "Distinctive Image Features from Scale-Invariant Keypoints", International Journal of Computer Vision, 2004.