Is your feature request related to a problem? Please describe.
If we are interested in getting an ID of a certain plague, we usually seek help in user forums. After some years you will by a microscope and try the ID by your self by comparing what you see with literature etc... Though this is a great approach, it is timecomsuming and the mismatch rate of the untrained may lead to false positives.
Describe the solution you'd like
Have a trained picture recognition algorithm - by using Maschine learning (ML) approach - which helps to get an ID with a high matching rate. Input is a picture of the plague taken by the user with a microscope and the used resolution rate.
Describe alternatives you've considered
None so far.
Additional context
ML is not the problem here. The challenge is to get a big enough picture test-set and reference imaging procedure for users who wants to use this approach.
Is your feature request related to a problem? Please describe. If we are interested in getting an ID of a certain plague, we usually seek help in user forums. After some years you will by a microscope and try the ID by your self by comparing what you see with literature etc... Though this is a great approach, it is timecomsuming and the mismatch rate of the untrained may lead to false positives.
Describe the solution you'd like Have a trained picture recognition algorithm - by using Maschine learning (ML) approach - which helps to get an ID with a high matching rate. Input is a picture of the plague taken by the user with a microscope and the used resolution rate.
Describe alternatives you've considered None so far.
Additional context ML is not the problem here. The challenge is to get a big enough picture test-set and reference imaging procedure for users who wants to use this approach.