http://www.emgu.com
Eliminate the matched features whose scale and rotation do not aggree with the majority's scale and rotation.

Namespace: Emgu.CV.Features2D
Assembly: Emgu.CV (in Emgu.CV.dll) Version: 2.3.0.1416 (2.3.0.1416)

Syntax

C#
public static int VoteForSizeAndOrientation(
	VectorOfKeyPoint modelKeyPoints,
	VectorOfKeyPoint observedKeyPoints,
	Matrix<int> indices,
	Matrix<byte> mask,
	double scaleIncrement,
	int rotationBins
)
Visual Basic
Public Shared Function VoteForSizeAndOrientation ( _
	modelKeyPoints As VectorOfKeyPoint, _
	observedKeyPoints As VectorOfKeyPoint, _
	indices As Matrix(Of Integer), _
	mask As Matrix(Of Byte), _
	scaleIncrement As Double, _
	rotationBins As Integer _
) As Integer
Visual C++
public:
static int VoteForSizeAndOrientation(
	VectorOfKeyPoint^ modelKeyPoints, 
	VectorOfKeyPoint^ observedKeyPoints, 
	Matrix<int>^ indices, 
	Matrix<unsigned char>^ mask, 
	double scaleIncrement, 
	int rotationBins
)

Parameters

modelKeyPoints
Type: Emgu.CV.Util..::..VectorOfKeyPoint
The keypoints from the model image
observedKeyPoints
Type: Emgu.CV.Util..::..VectorOfKeyPoint
The keypoints from the observed image
indices
Type: Emgu.CV..::..Matrix<(Of <(<'Int32>)>)>
The match indices matrix. indices[i, k] = j, indicates the j-th model descriptor is the k-th closest match to the i-th observed descriptor
mask
Type: Emgu.CV..::..Matrix<(Of <(<'Byte>)>)>
This is both input and output. This matrix indicates which row is valid for the matches.
scaleIncrement
Type: System..::..Double
This determins the different in scale for neighbour hood bins, a good value might be 1.5 (which means matched features in bin i+1 is scaled 1.5 times larger than matched features in bin i
rotationBins
Type: System..::..Int32
The numbers of bins for rotation, a good value might be 20 (which means each bin covers 18 degree)

Return Value

The number of non-zero elements in the resulting mask

See Also