Skip to main content

Table 1 Relationship between the number of training images and the performance of flowering detection

From: Automated characterization of flowering dynamics in rice using field-acquired time-series RGB images

Training number

5

15

30

50

100

300

Accuracy(+)

0.74± 0.05

0.81± 0.04

0.83± 0.03

0.79± 0.03

0.73± 0.02

0.64

TP rate(+)

0.65± 0.13

0.61± 0.12

0.59± 0.09

0.49± 0.08

0.31± 0.04

0.09

TN rate(+)

0.8 ± 0.09

0.95± 0.03

0.99± 0.00

0.99± 0.00

1 ± 0.00

1.0

  1. +Accuracy, TP rate, and TN rate, were defined as follows:
  2. \( \mathrm{Accuracy}=\frac{\mathrm{TP} + \mathrm{T}\mathrm{N}}{\mathrm{TP} + \mathrm{F}\mathrm{P} + \mathrm{T}\mathrm{N} + \mathrm{F}\mathrm{N}},\mathrm{T}\mathrm{P}\mathrm{rate}=\frac{\mathrm{TP}}{\mathrm{TP}+\mathrm{F}\mathrm{N}},\mathrm{T}\mathrm{N}\ \mathrm{rate}=\frac{\mathrm{TP}}{\mathrm{FP}+\mathrm{T}\mathrm{N}} \)
  3. where TP, TN, FP, and FN represent the numbers of true positives, true negatives, false positives, and false negatives, respectively, of the confusion matrix.