• Welcome to BirdForum, the internet's largest birding community with thousands of members from all over the world. The forums are dedicated to wild birds, birding, binoculars and equipment and all that goes with it.

    Please register for an account to take part in the discussions in the forum, post your pictures in the gallery and more.
ZEISS DTI thermal imaging cameras. For more discoveries at night, and during the day.

Scottish gull - changing from YLG to LBB in Merlin? (1 Viewer)

LittleBitOfBreadNoCheese

Well-known member
Scotland
I saw this bird in flight some way off at first and thought it was a Herring Gull. I followed to where it landed to get some pics and then submitted the two below to Merlin Photo Id. The first one it said was a YLG but the closeup one where the angle/contrast is worse it then decided was an LBB. OK I know it wasn't actually as dark winged as the second picture suggests but its a bit disconcerting that that alone was enough to make a different diagnosis?
 

Attachments

  • DSC00231.JPG
    4.6 MB · Views: 56
  • DSC00240.JPG
    3.7 MB · Views: 44
I saw this bird in flight some way off at first and thought it was a Herring Gull. I followed to where it landed to get some pics and then submitted the two below to Merlin Photo Id. The first one it said was a YLG but the closeup one where the angle/contrast is worse it then decided was an LBB. OK I know it wasn't actually as dark winged as the second picture suggests but its a bit disconcerting that that alone was enough to make a different diagnosis?
The bird is a graellsii Lesser Black-backed Gull. Even in that initial image, the upperparts are too dark for a Yellow-legged Gull, and please also note the extent of head streaking, more extensive than may be expected in Yellow-legged. Also, Yellow-legged Gull is quite notable in Scotland, not that probability alone should prove a basis for a solid identification.
Regards,
Harry
 
Not really - or not unless you're easily disconcerted and feel you should be able to trust AI. Merlin is definitely remarkable, but it's equally definitely not reliable.
I work as a programmer and have done a bit of machine learning although not in image recognition so I'm intrigued by the use of neural networks in birding. I've used birdNET quite a bit now and most of the time it is pretty good even with 2 or 3 different birds in the recording. It has significantly helped me learn. On the other hand it does have what I would call howlers now and again and some regular false positives which you can learn. I've barely used Merlin so far so haven't built up a detailed picture of its quirks partly due to only just getting my new camera.
 
Warning! This thread is more than 3 years ago old.
It's likely that no further discussion is required, in which case we recommend starting a new thread. If however you feel your response is required you can still do so.

Users who are viewing this thread

Back
Top