[Paraview] Comparing two curves

[David Pont]

Hi Abdul,
  I am currently doing some work comparing distributions using the Kolmogorov-Smirnov (KS) test. This technique is probably not directly applicable but the basic approach may be? My understanding is the basic metric used is the vertical deviation between the two cumulative distribution curves. Perhaps this methodology can be applied to create a similarity metric for arbitrary curves? As with the KS test you may want to normalise or standardise the two curves first.

  regards Dave

David Pont
Scientist - Forest Management Science
Scion
49 Sala Street, Private Bag 3020, Rotorua 3046, New Zealand
DDI +64 7 343 5663
www.scionresearch.com<http://www.scionresearch.com/>

[cid:image001.png at 01CD08D4.0C382EF0]

From: paraview-bounces at paraview.org [mailto:paraview-bounces at paraview.org] On Behalf Of Abdullahi Sanusi
Sent: Friday, 23 March 2012 12:24 a.m.
To: paraview at paraview.org
Subject: [Paraview] Comparing two curves

Hi All,
Given two curves A and B with point set A={p1,q1,r1} and B={p2,q2,r2}. I want to determine if the two curves are the same (similar) and compute the similarity score. Your kind advice will be well appreciated.
Cheer,
Abdul.

________________________________


This e-mail and any attachments may contain information which is confidential or subject to copyright. If you receive this e-mail in error, please delete it.
Scion does not accept responsibility for anything in this e-mail which is not provided in the course of Scion's usual business or for any computer virus, data corruption, interference or delay arising from this e-mail.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.paraview.org/pipermail/paraview/attachments/20120323/652cdd70/attachment.htm>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image001.png
Type: image/png
Size: 1857 bytes
Desc: image001.png
URL: <http://www.paraview.org/pipermail/paraview/attachments/20120323/652cdd70/attachment.png>