[GRASSLIST:4108] problems with r.le

[Leonardo Lami]

Hi,
I have a problem using r.le programs:
I have a raster with various patches with only one category value and with 
background null.
If I use a moving window for the r.le.patch with att=s1 (mean patch size) I 
have an output raster where every cells take the value of the result of the 
analysis of the corresponding window.
If i look the raster output all isolated patches seem correct.
The problem is that I can see error near the boundary of some patches in the 
side that have other patches neighbour.

The error is more extended if the moving window is bigger.
Someone had the same problems?

Thanks
Leonardo Lami