Module opencv::features2d

2D Features Framework

Feature Detection and Description

Descriptor Matchers

Matchers of keypoint descriptors in OpenCV have wrappers with a common interface that enables you to easily switch between different algorithms solving the same problem. This section is devoted to matching descriptors that are represented as vectors in a multidimensional space. All objects that implement vector descriptor matchers inherit the DescriptorMatcher interface.

Drawing Function of Keypoints and Matches

Object Categorization

This section describes approaches based on local 2D features and used to categorize objects.

Hardware Acceleration Layer

Modules

• prelude

Structs

• BFMatcher
  Brute-force descriptor matcher.
• BOWImgDescriptorExtractor
  Class to compute an image descriptor using the bag of visual words.
• BOWKMeansTrainer
  kmeans -based class to train visual vocabulary using the bag of visual words approach. :
• Feature2D
• FlannBasedMatcher
  Flann-based descriptor matcher.
• KeyPointsFilter
  A class filters a vector of keypoints.
• SimpleBlobDetector_Params

Enums

• AKAZE_DescriptorType
• AgastFeatureDetector_DetectorType
• DescriptorMatcher_MatcherType
• DrawMatchesFlags
• FastFeatureDetector_DetectorType
• KAZE_DiffusivityType
• ORB_ScoreType

Constants

• AKAZE_DESCRIPTOR_KAZE
• AKAZE_DESCRIPTOR_KAZE_UPRIGHT
  Upright descriptors, not invariant to rotation
• AKAZE_DESCRIPTOR_MLDB
• AKAZE_DESCRIPTOR_MLDB_UPRIGHT
  Upright descriptors, not invariant to rotation
• AgastFeatureDetector_AGAST_5_8
• AgastFeatureDetector_AGAST_7_12d
• AgastFeatureDetector_AGAST_7_12s
• AgastFeatureDetector_NONMAX_SUPPRESSION
• AgastFeatureDetector_OAST_9_16
• AgastFeatureDetector_THRESHOLD
• DescriptorMatcher_BRUTEFORCE
• DescriptorMatcher_BRUTEFORCE_HAMMING
• DescriptorMatcher_BRUTEFORCE_HAMMINGLUT
• DescriptorMatcher_BRUTEFORCE_L1
• DescriptorMatcher_BRUTEFORCE_SL2
• DescriptorMatcher_FLANNBASED
• DrawMatchesFlags_DEFAULT
  Output image matrix will be created (Mat::create), i.e. existing memory of output image may be reused. Two source image, matches and single keypoints will be drawn. For each keypoint only the center point will be drawn (without the circle around keypoint with keypoint size and orientation).
• DrawMatchesFlags_DRAW_OVER_OUTIMG
  Output image matrix will not be created (Mat::create). Matches will be drawn on existing content of output image.
• DrawMatchesFlags_DRAW_RICH_KEYPOINTS
  For each keypoint the circle around keypoint with keypoint size and orientation will be drawn.
• DrawMatchesFlags_NOT_DRAW_SINGLE_POINTS
  Single keypoints will not be drawn.
• FastFeatureDetector_FAST_N
• FastFeatureDetector_NONMAX_SUPPRESSION
• FastFeatureDetector_THRESHOLD
• FastFeatureDetector_TYPE_5_8
• FastFeatureDetector_TYPE_7_12
• FastFeatureDetector_TYPE_9_16
• KAZE_DIFF_CHARBONNIER
• KAZE_DIFF_PM_G1
• KAZE_DIFF_PM_G2
• KAZE_DIFF_WEICKERT
• ORB_FAST_SCORE
• ORB_HARRIS_SCORE

Traits

• AKAZE
  Class implementing the AKAZE keypoint detector and descriptor extractor, described in ANB13.
• AKAZEConst
  Constant methods for crate::features2d::AKAZE
• AffineFeature
  Class for implementing the wrapper which makes detectors and extractors to be affine invariant, described as ASIFT in YM11 .
• AffineFeatureConst
  Constant methods for crate::features2d::AffineFeature
• AgastFeatureDetector
  Wrapping class for feature detection using the AGAST method. :
• AgastFeatureDetectorConst
  Constant methods for crate::features2d::AgastFeatureDetector
• BFMatcherTrait
  Mutable methods for crate::features2d::BFMatcher
• BFMatcherTraitConst
  Constant methods for crate::features2d::BFMatcher
• BOWImgDescriptorExtractorTrait
  Mutable methods for crate::features2d::BOWImgDescriptorExtractor
• BOWImgDescriptorExtractorTraitConst
  Constant methods for crate::features2d::BOWImgDescriptorExtractor
• BOWKMeansTrainerTrait
  Mutable methods for crate::features2d::BOWKMeansTrainer
• BOWKMeansTrainerTraitConst
  Constant methods for crate::features2d::BOWKMeansTrainer
• BOWTrainer
  Abstract base class for training the bag of visual words vocabulary from a set of descriptors.
• BOWTrainerConst
  Constant methods for crate::features2d::BOWTrainer
• BRISK
  Class implementing the BRISK keypoint detector and descriptor extractor, described in LCS11 .
• BRISKConst
  Constant methods for crate::features2d::BRISK
• DescriptorMatcher
  Abstract base class for matching keypoint descriptors.
• DescriptorMatcherConst
  Constant methods for crate::features2d::DescriptorMatcher
• FastFeatureDetector
  Wrapping class for feature detection using the FAST method. :
• FastFeatureDetectorConst
  Constant methods for crate::features2d::FastFeatureDetector
• Feature2DTrait
  Mutable methods for crate::features2d::Feature2D
• Feature2DTraitConst
  Constant methods for crate::features2d::Feature2D
• FlannBasedMatcherTrait
  Mutable methods for crate::features2d::FlannBasedMatcher
• FlannBasedMatcherTraitConst
  Constant methods for crate::features2d::FlannBasedMatcher
• GFTTDetector
  Wrapping class for feature detection using the goodFeaturesToTrack function. :
• GFTTDetectorConst
  Constant methods for crate::features2d::GFTTDetector
• KAZE
  Class implementing the KAZE keypoint detector and descriptor extractor, described in ABD12 .
• KAZEConst
  Constant methods for crate::features2d::KAZE
• KeyPointsFilterTrait
  Mutable methods for crate::features2d::KeyPointsFilter
• KeyPointsFilterTraitConst
  Constant methods for crate::features2d::KeyPointsFilter
• MSER
  Maximally stable extremal region extractor
• MSERConst
  Constant methods for crate::features2d::MSER
• ORB
  Class implementing the ORB (oriented BRIEF) keypoint detector and descriptor extractor
• ORBConst
  Constant methods for crate::features2d::ORB
• SIFT
  Class for extracting keypoints and computing descriptors using the Scale Invariant Feature Transform (SIFT) algorithm by D. Lowe Lowe04 .
• SIFTConst
  Constant methods for crate::features2d::SIFT
• SimpleBlobDetector
  Class for extracting blobs from an image. :
• SimpleBlobDetectorConst
  Constant methods for crate::features2d::SimpleBlobDetector

Functions

• agast
  Detects corners using the AGAST algorithm
• agast_with_type
  Detects corners using the AGAST algorithm
• compute_recall_precision_curve
• draw_keypoints
  Draws keypoints.
• draw_matches
  Draws the found matches of keypoints from two images.
• draw_matches_1
  Draws the found matches of keypoints from two images.
• draw_matches_knn
  C++ default parameters
• evaluate_feature_detector
  
  Functions to evaluate the feature detectors and [generic] descriptor extractors * **
• fast
  Detects corners using the FAST algorithm
• fast_with_type
  Detects corners using the FAST algorithm
• get_nearest_point
• get_recall

Type Definitions

• AffineDescriptorExtractor
• AffineFeatureDetector
• DescriptorExtractor
  Extractors of keypoint descriptors in OpenCV have wrappers with a common interface that enables you to easily switch between different algorithms solving the same problem. This section is devoted to computing descriptors represented as vectors in a multidimensional space. All objects that implement the vector descriptor extractors inherit the DescriptorExtractor interface.
• FeatureDetector
  Feature detectors in OpenCV have wrappers with a common interface that enables you to easily switch between different algorithms solving the same problem. All objects that implement keypoint detectors inherit the FeatureDetector interface.
• SiftDescriptorExtractor
• SiftFeatureDetector