Module opencv::xfeatures2d

Extra 2D Features Framework

Experimental 2D Features Algorithms

This section describes experimental algorithms for 2d feature detection.

Non-free 2D Features Algorithms

This section describes two popular algorithms for 2d feature detection, SIFT and SURF, that are known to be patented. You need to set the OPENCV_ENABLE_NONFREE option in cmake to use those. Use them at your own risk.

Experimental 2D Features Matching Algorithm

This section describes the GMS (Grid-based Motion Statistics) matching strategy.

Structs

BriefDescriptorExtractor	Class for computing BRIEF descriptors described in calon2010 .
Elliptic_KeyPoint	Elliptic region around an interest point.
FREAK	Class implementing the FREAK (Fast Retina Keypoint) keypoint descriptor, described in AOV12 .
HarrisLaplaceFeatureDetector	Class implementing the Harris-Laplace feature detector as described in Mikolajczyk2004.
LATCH	latch Class for computing the LATCH descriptor. If you find this code useful, please add a reference to the following paper in your work: Gil Levi and Tal Hassner, "LATCH: Learned Arrangements of Three Patch Codes", arXiv preprint arXiv:1501.03719, 15 Jan. 2015
LUCID	Class implementing the locally uniform comparison image descriptor, described in LUCID
MSDDetector	Class implementing the MSD (Maximal Self-Dissimilarity) keypoint detector, described in Tombari14.
SIFT	Class for extracting keypoints and computing descriptors using the Scale Invariant Feature Transform (SIFT) algorithm by D. Lowe Lowe04 .
StarDetector	The class implements the keypoint detector introduced by Agrawal08, synonym of StarDetector. :

Constants

DAISY_NRM_FULL
DAISY_NRM_NONE
DAISY_NRM_PARTIAL
DAISY_NRM_SIFT
FREAK_NB_ORIENPAIRS
FREAK_NB_PAIRS
FREAK_NB_SCALES
PCTSignatures_GAUSSIAN	block formula
PCTSignatures_HEURISTIC	block formula
PCTSignatures_L1
PCTSignatures_L2
PCTSignatures_L2SQUARED
PCTSignatures_L5
PCTSignatures_L0_5
PCTSignatures_L0_25
PCTSignatures_L_INFINITY
PCTSignatures_MINUS	block formula
PCTSignatures_NORMAL	Generate points with normal (gaussian) distribution.
PCTSignatures_REGULAR	Generate points in a regular grid.
PCTSignatures_UNIFORM	Generate numbers uniformly.

Traits

AffineFeature2D	Class implementing affine adaptation for key points.
BoostDesc	Class implementing BoostDesc (Learning Image Descriptors with Boosting), described in Trzcinski13a and Trzcinski13b.
DAISY	Class implementing DAISY descriptor, described in Tola10
PCTSignatures	Class implementing PCT (position-color-texture) signature extraction as described in KrulisLS16. The algorithm is divided to a feature sampler and a clusterizer. Feature sampler produces samples at given set of coordinates. Clusterizer then produces clusters of these samples using k-means algorithm. Resulting set of clusters is the signature of the input image.
PCTSignaturesSQFD	Class implementing Signature Quadratic Form Distance (SQFD). @see Christian Beecks, Merih Seran Uysal, Thomas Seidl. Signature quadratic form distance. In Proceedings of the ACM International Conference on Image and Video Retrieval, pages 438-445. ACM, 2010. BeecksUS10
SURF	Class for extracting Speeded Up Robust Features from an image Bay06 .
VGG	Class implementing VGG (Oxford Visual Geometry Group) descriptor trained end to end using "Descriptor Learning Using Convex Optimisation" (DLCO) aparatus described in Simonyan14.

Functions

fast_for_point_set	Estimates cornerness for prespecified KeyPoints using the FAST algorithm
match_gms	GMS (Grid-based Motion Statistics) feature matching strategy by Bian2017gms .