Fig. 2

Precision and recall for the VGG16 network with various classifiers. The color bars represent Pre and Rec in this order. The classifiers are arranged as follows: SVM, RBF, \(\gamma =\)“scale”, C=15;   SVM, RBF, \(\gamma =10^{-7},\) C=10;   \(\underline{\text {SVM, RBF,}\, \gamma =10^{-7}, \text {C}=15;}\) SVM, RBF, \(\gamma =10^{-7},\) C=20;    SVM, polynomial of deg = 2;   SVM, polynomial of deg = 3; DT, min−samples−leaf = 2; DT, min−samples−leaf = 3;    RF, n−estimators = 100;   RF, n−estimators = 200. The extra parameters of the DT are: criterion = “gini”, random−state = 42, and max−depth =3