You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
implement in the preprocessing phase remove background and keep only most likely leaf
Motivation
suppress a bad effect of background objects, probably would be also useful to. get some attention map and see if any decision was made other than leaf focus
We don't have grabcut. But still I see some false positives. The best would be detecting depth or large gradient intensity to filter out or add an attention loss
🚀 Feature
implement in the preprocessing phase remove background and keep only most likely leaf
Motivation
suppress a bad effect of background objects, probably would be also useful to. get some attention map and see if any decision was made other than leaf focus
Pitch
see OpenCV version https://www.kaggle.com/victorlouisdg/plant-pathology-opencv-background-removal
Alternatives
can we do it in Kornia too? @edgarriba
Additional context
The text was updated successfully, but these errors were encountered: