[R-sig-Geo] smoothing contours (image.smooth)

F. De Sales fhds2000 at yahoo.com
Fri Apr 25 20:53:14 CEST 2008


    Thanks for your help.
    I tried different dx, dy and theta values,
however, the results matrix was too smooth and some of
the main feature disappeared.
    I was just looking to get the contour lines
slightly smoother.
    Thank you.
    
--- Roger Bivand <Roger.Bivand at nhh.no> wrote:

> On Thu, 24 Apr 2008, F. De Sales wrote:
> 
> >
> >    Hi all,
> >    I was wondering if anyone in here is familiar
> with
> > the command "image.smooth".
> >    How can set the arguments dx, dy and theta to
> > minimize the smoothing?
> 
> Read ?image.smooth in the fields package, and run
> the examples with 
> various values until you can see what they do, with
> the alternative of 
> reading the source code.
> 
> >    Is there any other way to get smoother contour
> > maps, ie, without so many sharp corners?
> 
> The function is not adding any information, so if
> there are sharp corners 
> in the contours, then there are sharp corners in the
> data, and smoothing 
> is not your friend. One possibility is to change the
> resolution of the 
> image, which should remove sharp boundaries that are
> only artefacts of the 
> resolution - for example by interpolating to a
> denser grid.
> 
> Roger
> 
> >    I'd appreciate any help.
> >    Thank you very much.
> >
> >
> >
> >
> >     
>
____________________________________________________________________________________
> >
> > [[elided Yahoo spam]]
> >
> > _______________________________________________
> > R-sig-Geo mailing list
> > R-sig-Geo at stat.math.ethz.ch
> > https://stat.ethz.ch/mailman/listinfo/r-sig-geo
> >
> 
> -- 
> Roger Bivand
> Economic Geography Section, Department of Economics,
> Norwegian School of
> Economics and Business Administration, Helleveien
> 30, N-5045 Bergen,
> Norway. voice: +47 55 95 93 55; fax +47 55 95 95 43
> e-mail: Roger.Bivand at nhh.no
> 
> 



      ____________________________________________________________________________________

[[elided Yahoo spam]]




More information about the R-sig-Geo mailing list