Finds (with high probability) the k nearest neighbors in tr for each of the given (row-)vectors in desc, using best-bin-first searching ([Beis97]). The complexity of the entire operation is at most O(m*emax*log2(n)), where n is the number of vectors in the tree

Namespace:  Emgu.CV
Assembly:  Emgu.CV (in Emgu.CV.dll) Version: 2.0.1.0 (2.0.1.0)

Syntax

C#
public void FindFeatures(
	float[][] descriptors,
	out Matrix<int> results,
	out Matrix<double> dist,
	int k,
	int emax
)
Visual Basic (Declaration)
Public Sub FindFeatures ( _
	descriptors As Single()(), _
	<OutAttribute> ByRef results As Matrix(Of Integer), _
	<OutAttribute> ByRef dist As Matrix(Of Double), _
	k As Integer, _
	emax As Integer _
)
Visual C++
public:
void FindFeatures(
	array<array<float>^>^ descriptors, 
	[OutAttribute] Matrix<int>^% results, 
	[OutAttribute] Matrix<double>^% dist, 
	int k, 
	int emax
)

Parameters

descriptors
Type: array< array< System..::.Single >[]()[] >[]()[]
The m feature descriptors to be searched from the feature tree
results
Type: Emgu.CV..::.Matrix<(Of <(Int32>)>) %
The results of the best k matched from the feature tree. A m x k matrix. Contains -1 in some columns if fewer than k neighbors found. For each row the k neareast neighbors are not sorted. To findout the closet neighbour, look at the output matrix dist.
dist
Type: Emgu.CV..::.Matrix<(Of <(Double>)>) %
A m x k matrix of the distances to k nearest neighbors
k
Type: System..::.Int32
The number of neighbors to find
emax
Type: System..::.Int32
For k-d tree only: the maximum number of leaves to visit. Use 20 if not sure

See Also