A New Data Model for the Privacy Protection of Medical Images

Table 1

Comparison of recognition performance among datasets from our proposed EVCS, Fabio’s method, and normal datasets.

Metric	EVCS	Fabio’s method	Normal
Accuracy	0.94	83.8	0.97
Recall	0.93	—	0.96
Precision	0.96	—	0.98
f1-score	0.93	—	0.97