CStats:YpMean
The YpMean method computes the mean value of
a data sample using "Yp Mean" estimation to reduce the influence of
deviant pixels. The sample may be a Lua table or a class object of
type CImage,
CArray, or CMatrix. For CImage
and CMatrix objects, an optional CRect object can be used to define the points
used in the calculation.
Syntax
|
nMean, nStdDev = CStats:YpMean( table,
nExp )
nMean, nStdDev = CStats:YpMean( CImage, nExp )
nMean, nStdDev = CStats:YpMean( CImage, nExp, CRect )
nMean, nStdDev = CStats:YpMean( CArray, nExp )
nMean, nStdDev = CStats:YpMean( CArray, nExp, CRect )
nMean, nStdDev = CStats:YpMean( CMatrix, nExp )
where
 table is a lua table containing the data.
CImage,
CArray, and CMatrix
are class objects containing the data to measure,
CRect is
a CRect rectangle
object that defines the region to measure.
|
nExp is the exponent used in the Yp Mean
calculation.
nMean and nStdDev are the yp-power mean and standard
deviation, respectively. On failure, 0,0 is returned.
This method assigns weights to values based upon
their distance from the mean value. No rejection ("clipping") is
performed. In contrast to the geometric mean, this method can be
tuned to assign less weight to positive values or less weight to
negative values, and the severity of the weighting scheme may be
adjusted. The positive or negative tail bias depends upon the value
of the exponent parameter and the severity of the weighting depends
upon the absolute value of the exponent parameter.
For an exponent parameter of value y, the statistic is
computed by summing each sample member x raised to the power y as shown below. (Note: The symbol ^ denotes
raising a number to a power, as in 2^3 = 8):
Total
= Sum(x^y)
The resulting
mean value is then re-scaled as
Statistic
= Total^(1/y) .
Thus
p=0 is invalid.
Do not use.
p>0 gives
higher weight to positive outliers.
p<0 gives
lower weight to negative outliers.
Examples
Suppose a CImage I and a CRect R exist. The
following script returns the Yp Mean value inside a rectangle on
the image:
|
nVal = S:YpMean( I, 0.25,
R )
|
|
|
Printf("mean=%lg\n", nVal)
|
|
The following script returns the Yp
mean value for a table of data using Y-power value 0.4:
|
S =
CStats:new()
|
|
|
t = {
4, 4, 2, 5, 6.4, -1.42, -12, 3.4 }
|
|
|
Printf("mean=%lg\n", S:YpMean(t,0.4)
)
|
|
Related
Topics