Detecting spikes of wheat plants using neural networks with Laws texture energy

Table 3 Accuracy of the classification

	Training	Testing	Validation	Total
Spike samples (pixels)	13,372	2890	2779	19,041
Leaf samples (pixels)	53,265	11,389	11,500	76,154
TP rate^a (%)	80.2	79	78.8	79.9
TN rate^a (%)	95.7	95.6	95.9	95.7
Accuracy^a(%)	92.5	92.3	92.4	92.4

^aAccuracy, TP rate and TN rate were defined as follows:
\(Accuracy = \frac{TP + TN}{TP + FP + TN + FN}\); \(Tprate = \frac{TP}{TP + FN}\); \(TNrate = \frac{TN}{FP + TN}\)
where TP, TN, FP, and FN represent the numbers of true positives, true negatives, false positives, and false negatives, respectively

ISSN: 1746-4811