Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Identify Plants with an App

plantsnap.net

Post reply on HN
Print view View original

81–90 of 117 posts

Re: Identify Plants with an App

#81

Post by jamessb »

dharma1 wrote: post #31

I did this for common plant diseases using Tensorflow on Android when learning how to use TF last year. Found the accuracy to be not that great with real world images that are not in the dataset (with a dataset of 50,000 images from PlantVillage). I think there are just too many visual similarities between various plants (especially when taken from various angles) that the network doesn't focus on the right things. D…

>I think there are just too many visual similarities between various plants

I get the impression that you tried to train a single classifier to diagnose disease in any species in the PlantVillage database.

You might get better results by training a separate classifier for each plant species (or starting with just one species, such as tomato, for which PlantVillage has 10 disease categories). A farmer knows what crop they're growing, so can select the correct classifier when they submit a photo.

Re: Identify Plants with an App

#82

Post by gozzoo »

This is very cool. I've been thinking about something similar, but only about mushrooms. Some people in my country pick wild mushrooms and sometimes it's very difficult to distinguish between the edible and the poisonous types. Such application, if existed could save many lives. The same concept could be used for other plants that people gather, like herbs and wild berries.

Re: Identify Plants with an App

#83

Post by Insanity »

Mytruthlies wrote: post #71

This is really cool. IF only I could find an app that does this with bugs.

Why do you want an app with bugs?!

But on a more serious note, I would appreciate that as well, but it might be harder to take a good picture of a bug by which it is identifiable?

I'm always impressed by these type of apps though and would love making one myself

Re: Identify Plants with an App

#84

Post by specialist »

dharma1 wrote: post #31

I did this for common plant diseases using Tensorflow on Android when learning how to use TF last year. Found the accuracy to be not that great with real world images that are not in the dataset (with a dataset of 50,000 images from PlantVillage). I think there are just too many visual similarities between various plants (especially when taken from various angles) that the network doesn't focus on the right things. D…

Nice. Will check it out.

Just knowing what questions to ask, what a bight could be would be very helpful to us plebes.

Re: Identify Plants with an App

#85

Post by specialist »

mrgreenfur wrote: post #78

When can we get this for identifying plants/animals/rocks/fungus/etc in the wild? Would love this on a phone when hiking.

Me too.

I volunteered at Audubon for a decade. I've got all the books, charts. I hike and camp. I can't identify rocks, birds, fish, trees, clouds, etc to save my life.

Square peg, round hole.

Re: Identify Plants with an App

#86

Post by dharma1 »

jamessb wrote: post #81
dharma1 wrote: post #31

I did this for common plant diseases using Tensorflow on Android when learning how to use TF last year. Found the accuracy to be not that great with real world images that are not in the dataset (with a dataset of 50,000 images from PlantVillage). I think there are just too many visual similarities between various plants (especially when taken from various angles) that the network doesn't focus on the right things. D…

>I think there are just too many visual similarities between various plants I get the impression that you tried to train a single classifier to diagnose disease in any species in the PlantVillage database. You might get better results by training a separate classifier for each plant species (or starting with just one species, such as tomato, for which PlantVillage has 10 disease categories). A farmer knows what crop…

Great suggestion, that's the approach I've been looking at most recently (manual selection of crop first, then classifier for only that crop's diseases) and it does give better results. Still, many plant diseases can look quite similar - more training data once we get it (and more variety in the photos) should help accuracy

Re: Identify Plants with an App

#87

Post by make3 »

mrgreenfur wrote: post #78

When can we get this for identifying plants/animals/rocks/fungus/etc in the wild? Would love this on a phone when hiking.

this is made with convnets. so just point me to a dataset with a thousand examples per type, and I'll give you a working app in days. of course, finding and preparing that data is the real challenge

Re: Identify Plants with an App

#88

Post by make3 »

dharma1 wrote: post #31

I did this for common plant diseases using Tensorflow on Android when learning how to use TF last year. Found the accuracy to be not that great with real world images that are not in the dataset (with a dataset of 50,000 images from PlantVillage). I think there are just too many visual similarities between various plants (especially when taken from various angles) that the network doesn't focus on the right things. D…

50k images is too few for that many classes

Re: Identify Plants with an App

#90

Post by pvaldes »

folli wrote: post #20
hyperpallium wrote: post #4

Botantical classification is interesting but difficult. Once trained, it's fast enough, but can "deep learning" be anywhere near accurate enough? I'd guess there'd be a focus on salient botantical features for classification, and perhaps the human can be enlisted to circle them out. There could be a "twenty questions"-type narrowing down, perhaps using images.

Dichotomous keys are the standard in taxonomy for species identification since centuries. It's basically a binary search tree, generated by hand. https://en.wikipedia.org/wiki/Single-access_key

Dichotomous keys are mostly useless when you deal with photos. For some reason people always find the most useless chamera position when taking photos to unknown plants.
Post reply on HN