Skip to main content

Table 4 Average performance of models on images without soil background

From: Deep learning-based detection of seedling development

Model

Accuracy

Error

Sensitivity

Specificity

Precision

False positive rate

Multi-class CNN

0.80 ± 0.19

0.20 ± 0.19

0.85 ± 0.13

0.93 ± 0.07

0.85 ± 0.14

0.07 ± 0.07

2-class CNN’s

0.88 ± 0.18

0.12 ± 0.18

0.86 ± 0.10

0.95 ± 0.05

0.86 ± 0.11

0.05 ± 0.05

CNN-LSTM

0.90 ± 0.08

0.10 ± 0.07

0.87 ± 0.11

0.96 ± 0.03

0.88 ± 0.15

0.04 ± 0.04

ConvLSTM

0.81 ± 0.11

0.21 ± 0.09

0.85 ± 0.03

0.92 ± 0.09

0.85 ± 0.12

0.07 ± 0.10