naturerecordists
[Top] [All Lists]

Re: Match-to-sample software?

Subject: Re: Match-to-sample software?
From: Walter Knapp <>
Date: Mon, 09 Sep 2002 12:51:39 -0400
Wild Sanctuary wrote:
> 
> I got word back in March that there is a team of two fellas at Oxford
> or Cambridge in the UK who have developed reasonable match-to-sample
> software but have been unable to track them down. Anyone know who
> that might be?

Well, it's from Australia, and it was about frogcall ID, but does this
sound like it?

http://www.cse.unsw.edu.au/~andrewt/papers/frog_iaai96/frog_iaai96.html

This is the most hopeful thing I've seen, I've been meaning to follow up
on it and see how it would do on Georgia's frogs. With today's faster
computers it might be pretty good as it could make finer discriminations.

 I saw a report by someone who had used the system to evaluate if ATRAC
was going to mess it up. No problem with ATRAC recorded material, I'd
have been surprised if there was. It did sound like this was having a
fairly high success rate ID'ing between a choice of 22 frogs. It has to
be trained to the calls you want it to work with so it's probably going
to be something that would have to be trained to a local population.

Walt



________________________________________________________________________
________________________________________________________________________

<Prev in Thread] Current Thread [Next in Thread>
Admin

The University of NSW School of Computer and Engineering takes no responsibility for the contents of this archive. It is purely a compilation of material sent by many people to the naturerecordists mailing list. It has not been checked for accuracy nor its content verified in any way. If you wish to get material removed from the archive or have other queries about the archive e-mail Andrew Taylor at this address: andrewt@cse.unsw.EDU.AU