Fig. 5: The improved results of the CNN model and the size classification of lettuce heads. | Horticulture Research

Fig. 5: The improved results of the CNN model and the size classification of lettuce heads.

From: Combining computer vision and deep learning to enable ultra-scale aerial phenotyping and precision agriculture: A case study of lettuce production

Fig. 5

a Wrongly detected lettuces in very bright regions and overly counted lettuces in very dark regions, in a one-million-head field. b Enhanced training datasets to retrain the model using the online-learning approach, which led to much better detection results. c A predefined colour code (small is coloured blue, medium is coloured green, and large is coloured red) is assigned to each recognised lettuce head across the field

Back to article page