Xfeatures2d

Objective-C

@interface Xfeatures2d : NSObject

Swift

class Xfeatures2d : NSObject

The Xfeatures2d module

Member classes: FREAK, StarDetector, BriefDescriptorExtractor, LUCID, LATCH, DAISY, MSDDetector, VGG, BoostDesc, PCTSignatures, PCTSignaturesSQFD, HarrisLaplaceFeatureDetector, SURF

Member enums: NormalizationType, DistanceFunction, PointDistribution, SimilarityFunction, KeypointLayout

Methods


                    
                    
                    +matchGMS:size2:keypoints1:keypoints2:matches1to2:matchesGMS:withRotation:withScale:thresholdFactor:

GMS (Grid-based Motion Statistics) feature matching strategy described in CITE: Bian2017gms .

Declaration

Objective-C

+ (void)matchGMS:(nonnull Size2i *)size1
              size2:(nonnull Size2i *)size2
         keypoints1:(nonnull NSArray<KeyPoint *> *)keypoints1
         keypoints2:(nonnull NSArray<KeyPoint *> *)keypoints2
        matches1to2:(nonnull NSArray<DMatch *> *)matches1to2
         matchesGMS:(nonnull NSMutableArray<DMatch *> *)matchesGMS
       withRotation:(BOOL)withRotation
          withScale:(BOOL)withScale
    thresholdFactor:(double)thresholdFactor;

Swift

class func matchGMS(size1: Size2i, size2: Size2i, keypoints1: [KeyPoint], keypoints2: [KeyPoint], matches1to2: [DMatch], matchesGMS: NSMutableArray, withRotation: Bool, withScale: Bool, thresholdFactor: Double)

Parameters

`size1`	Input size of image1.
`size2`	Input size of image2.
`keypoints1`	Input keypoints of image1.
`keypoints2`	Input keypoints of image2.
`matches1to2`	Input 1-nearest neighbor matches.
`matchesGMS`	Matches returned by the GMS matching strategy.
`withRotation`	Take rotation transformation into account.
`withScale`	Take scale transformation into account.
`thresholdFactor`	The higher, the less matches. @note Since GMS works well when the number of features is large, we recommend to use the ORB feature and set FastThreshold to 0 to get as many as possible features quickly. If matching results are not satisfying, please add more features. (We use 10000 for images with 640 X 480). If your images have big rotation and scale changes, please set withRotation or withScale to true.


                    
                    
                    +matchGMS:size2:keypoints1:keypoints2:matches1to2:matchesGMS:withRotation:withScale:

GMS (Grid-based Motion Statistics) feature matching strategy described in CITE: Bian2017gms .

Declaration

Objective-C

+ (void)matchGMS:(nonnull Size2i *)size1
           size2:(nonnull Size2i *)size2
      keypoints1:(nonnull NSArray<KeyPoint *> *)keypoints1
      keypoints2:(nonnull NSArray<KeyPoint *> *)keypoints2
     matches1to2:(nonnull NSArray<DMatch *> *)matches1to2
      matchesGMS:(nonnull NSMutableArray<DMatch *> *)matchesGMS
    withRotation:(BOOL)withRotation
       withScale:(BOOL)withScale;

Swift

class func matchGMS(size1: Size2i, size2: Size2i, keypoints1: [KeyPoint], keypoints2: [KeyPoint], matches1to2: [DMatch], matchesGMS: NSMutableArray, withRotation: Bool, withScale: Bool)

Parameters

`size1`	Input size of image1.
`size2`	Input size of image2.
`keypoints1`	Input keypoints of image1.
`keypoints2`	Input keypoints of image2.
`matches1to2`	Input 1-nearest neighbor matches.
`matchesGMS`	Matches returned by the GMS matching strategy.
`withRotation`	Take rotation transformation into account.
`withScale`	Take scale transformation into account. @note Since GMS works well when the number of features is large, we recommend to use the ORB feature and set FastThreshold to 0 to get as many as possible features quickly. If matching results are not satisfying, please add more features. (We use 10000 for images with 640 X 480). If your images have big rotation and scale changes, please set withRotation or withScale to true.


                    
                    
                    +matchGMS:size2:keypoints1:keypoints2:matches1to2:matchesGMS:withRotation:

GMS (Grid-based Motion Statistics) feature matching strategy described in CITE: Bian2017gms .

Declaration

Objective-C

+ (void)matchGMS:(nonnull Size2i *)size1
           size2:(nonnull Size2i *)size2
      keypoints1:(nonnull NSArray<KeyPoint *> *)keypoints1
      keypoints2:(nonnull NSArray<KeyPoint *> *)keypoints2
     matches1to2:(nonnull NSArray<DMatch *> *)matches1to2
      matchesGMS:(nonnull NSMutableArray<DMatch *> *)matchesGMS
    withRotation:(BOOL)withRotation;

Swift

class func matchGMS(size1: Size2i, size2: Size2i, keypoints1: [KeyPoint], keypoints2: [KeyPoint], matches1to2: [DMatch], matchesGMS: NSMutableArray, withRotation: Bool)

Parameters

`size1`	Input size of image1.
`size2`	Input size of image2.
`keypoints1`	Input keypoints of image1.
`keypoints2`	Input keypoints of image2.
`matches1to2`	Input 1-nearest neighbor matches.
`matchesGMS`	Matches returned by the GMS matching strategy.
`withRotation`	Take rotation transformation into account. @note Since GMS works well when the number of features is large, we recommend to use the ORB feature and set FastThreshold to 0 to get as many as possible features quickly. If matching results are not satisfying, please add more features. (We use 10000 for images with 640 X 480). If your images have big rotation and scale changes, please set withRotation or withScale to true.


                    
                    
                    +matchGMS:size2:keypoints1:keypoints2:matches1to2:matchesGMS:

GMS (Grid-based Motion Statistics) feature matching strategy described in CITE: Bian2017gms .

Declaration

Objective-C

+ (void)matchGMS:(nonnull Size2i *)size1
           size2:(nonnull Size2i *)size2
      keypoints1:(nonnull NSArray<KeyPoint *> *)keypoints1
      keypoints2:(nonnull NSArray<KeyPoint *> *)keypoints2
     matches1to2:(nonnull NSArray<DMatch *> *)matches1to2
      matchesGMS:(nonnull NSMutableArray<DMatch *> *)matchesGMS;

Swift

class func matchGMS(size1: Size2i, size2: Size2i, keypoints1: [KeyPoint], keypoints2: [KeyPoint], matches1to2: [DMatch], matchesGMS: NSMutableArray)

Parameters

`size1`	Input size of image1.
`size2`	Input size of image2.
`keypoints1`	Input keypoints of image1.
`keypoints2`	Input keypoints of image2.
`matches1to2`	Input 1-nearest neighbor matches.
`matchesGMS`	Matches returned by the GMS matching strategy. @note Since GMS works well when the number of features is large, we recommend to use the ORB feature and set FastThreshold to 0 to get as many as possible features quickly. If matching results are not satisfying, please add more features. (We use 10000 for images with 640 X 480). If your images have big rotation and scale changes, please set withRotation or withScale to true.


                    
                    
                    +matchLOGOS:keypoints2:nn1:nn2:matches1to2:

LOGOS (Local geometric support for high-outlier spatial verification) feature matching strategy described in CITE: Lowry2018LOGOSLG .

Declaration

Objective-C

+ (void)matchLOGOS:(nonnull NSArray<KeyPoint *> *)keypoints1
        keypoints2:(nonnull NSArray<KeyPoint *> *)keypoints2
               nn1:(nonnull IntVector *)nn1
               nn2:(nonnull IntVector *)nn2
       matches1to2:(nonnull NSArray<DMatch *> *)matches1to2;

Swift

class func matchLOGOS(keypoints1: [KeyPoint], keypoints2: [KeyPoint], nn1: IntVector, nn2: IntVector, matches1to2: [DMatch])

Parameters

`keypoints1`	Input keypoints of image1.
`keypoints2`	Input keypoints of image2.
`nn1`	Index to the closest BoW centroid for each descriptors of image1.
`nn2`	Index to the closest BoW centroid for each descriptors of image2.
`matches1to2`	Matches returned by the LOGOS matching strategy. @note This matching strategy is suitable for features matching against large scale database. First step consists in constructing the bag-of-words (BoW) from a representative image database. Image descriptors are then represented by their closest codevector (nearest BoW centroid).