A methodology of weed-crop classification based on autonomous models choosing and ensemble
share
Neural networks play an important role in crop-weed classification have high accuracy more than 95 yet it is indispensable in most traditional practices and researches. Moreover, classic training metric are not thoroughly compatible with farming tasks, that a model still have a noticeable chance of miss classifying crop to weed while it reach higher accuracy even more than 99 methodology of weed-crop classification based on autonomous models choosing and ensemble that could make models choosing and tunning automatically, and improve the prediction with high accuracy(>99 with low risk in incorrect predicting.
READ FULL TEXT
