Date: 2/14/26 3:11 pm From: Bill Kosar <bill_kosar...> Subject: Re: [cobirds] Juvenile western bluebird and Merlin
Image ID via AI is a very challenging area where a lot of work is being
done. There is a very strong focus on identifying melanoma using
two-dimension images taken in the doctor's office but the accuracy of
current software tools seems to be about 95% at best which is similar to
what dermatologists' accuracy is. They are using huge databases (20,000 or
more) of pictures of one particular type of cancer and a very experienced
dermatologist expects the AI tools to get better over time.
By contrast the database of juvenile western bluebirds (and other
juveniles) is probably very small so the Merlin model will not be that
accurate, for now. Merlin is making decisions based on a single image, if
you could give it images from multiple angles its accuracy would probably
be much better.
Bill
On Saturday, February 14, 2026 at 3:04:39 PM UTC-7 Caoimhín Perkins wrote:
> Correct me if I’m wrong and if Merlin is incomplete in its photos of
> immature western bluebirds and townsend’s solitaires, but the gape flange
> is yellow in this photo, which is a western bluebird trait, yes?
--
--
You received this message because you are subscribed to the Google Groups "Colorado Birds" group.
To post to this group, send email to <cobirds...>
For more options, visit this group at
http://groups.google.com/group/cobirds * All posts should be signed with the poster's full name and city. Include bird species and location in the subject line when appropriate.
* Join Colorado Field Ornithologists https://cobirds.org/membership/ ---
You received this message because you are subscribed to the Google Groups "Colorado Birds" group.
To unsubscribe from this group and stop receiving emails from it, send an email to cobirds+<unsubscribe...>
To view this discussion visit https://groups.google.com/d/msgid/cobirds/<609285a6-dced-4774-83c6-41090f9a77d9n...>
