Pl@ntNet is the world’s best social network is an interesting article and leads to a useful looking app.
Pl@ntNet is a plant identifier that combines algorithmic and social tools to identify plants.
An algorithm matches the digital image against a massive plant database and presents its best guesses as to what type of plant it is. The user who submitted the original image picks from a list of the most likely candidates, and ranks the probability the image is a match on a five-star scale. The community then vets each image, validating the identification or suggesting a new one.
The post has lots of interesting angles on the possible future of social networks, the indieweb and a nice personal touch. Highly recommended.
Last week I crowd sourced a flower identification, I ran the same image through Pl@ntNet this morning and had confirmation of the conclusion ‘we’ had reached1.
I made a couple more tests on the app and it seems to work really well. My one problem was that submitting photos uses the location you are at at the time of submission, not where I took the image (as far as I can see). Often I want to take a picture and bring it home to identify. I don’t want to give the impression that a Scottish hill flower is at home in Glasgow city! I can of course just id flowers without uploading them but the organisation wants people to add to the collection in the name of citizen science.
I’d recommend the app itself too, it seems to work very well, could be useful for outdoor learning and Pl@ntNet’s practices and principles sound great: open and thoughtful.