CStats:MtmSigmaClipMean CStats:Sdev

CStats:RankClipMean


The RankClipMean method computes the mean value inside a rectangular region of the image, clipping pixel values below and above the specified rank percentiles. The rectangle and image must have been previously initialized for the CStats object.

Syntax

nMean = CStats:RankClipMean( nHigh, nLow )

Remarks

The calculated statistic computes the mean value using data above a low percentile and below a high percentile rank. These rank percentiles are absolute on the scale 0 to 100 percent. For example, passing the argumentsnLow=5 and nHigh=95 calculates the region mean value after rejecting data in both the lower 5 percentile and the upper 5 percentile of the sample.

This method uses the same algorithm as the RankClip method of the CImCombine class.

Example

Suppose a CImage I and a CRect R exist. The following script returns the rank clipped mean value inside a rectangle on the image:

 

S = CStats:new()

-- create a CStats object

S:Init( I, R )

-- specify CImage and CRect to measure

nVal = S:RankClipMean(95,5)

-- mean value between 5th and 95th percentile

Printf("mean=%lg\n", nVal)

-- list the results

Related Topics

CStats, CImage, CRect, MinMaxClipMean, SigmaClipMean, AlphaClipMean