Particles Detection System with CR-39 Based on Deep Learning

Table 1

Confusion matrix of our U-Net model. As can be seen from the definition of accuracy, the two important quantities that contribute to high accuracy are true positives (TP) and true negatives (TN).

Real	Predicted
	Positives: 1,782	Negatives: 2,727
Positives: 1,697	TP: 1,665	FN: 32
Negatives: 2,812	FP: 117	TN: 2,695

Threshold: 0.4.