Emgu CV Library Documentation
cvCalcCovarMatrix Method (vects, count, covMat, avg, flags)
NamespacesEmgu.CVCvInvokecvCalcCovarMatrix(array<IntPtr>[]()[], Int32, IntPtr, IntPtr, COVAR_METHOD)

www.emgu.com/wiki
Calculates the covariation matrix and, optionally, mean vector of the set of input vectors.
Declaration Syntax
C#Visual BasicVisual C++
public static void cvCalcCovarMatrix(
	IntPtr[] vects,
	int count,
	IntPtr covMat,
	IntPtr avg,
	COVAR_METHOD flags
)
Public Shared Sub cvCalcCovarMatrix ( _
	vects As IntPtr(), _
	count As Integer, _
	covMat As IntPtr, _
	avg As IntPtr, _
	flags As COVAR_METHOD _
)
public:
static void cvCalcCovarMatrix(
	array<IntPtr>^ vects, 
	int count, 
	IntPtr covMat, 
	IntPtr avg, 
	COVAR_METHOD flags
)
Parameters
vects (array< IntPtr >[]()[])
The input vectors. They all must have the same type and the same size. The vectors do not have to be 1D, they can be 2D (e.g. images) etc
count (Int32)
The number of input vectors
covMat (IntPtr)
The output covariation matrix that should be floating-point and square
avg (IntPtr)
The input or output (depending on the flags) array - the mean (average) vector of the input vectors.
flags (COVAR_METHOD)
The operation flags
Remarks
The function can be used for PCA, for comparing vectors using Mahalanobis distance etc.

Assembly: Emgu.CV (Module: Emgu.CV) Version: 1.5.0.0 (1.5.0.0)