Table 4.

Continuation of Table 3.

Extractors	Classifiers	Accuracy	Precision	F1 Score	Recall
ResNet50	Naive Bayes	63.16 ± 0.00	31.58 ± 0.00	38.71 ± 0.00	50.00 ± 0.00
	MLP	66.32 ± 1.94	82.62 ± 0.68	47.17 ± 4.62	54.29 ± 2.63
	kNN	87.68 ± 3.40	89.01 ± 3.97	86.07 ± 3.88	84.71 ± 4.00
	RF	85.26 ± 4.16	86.81 ± 4.03	82.97 ± 5.35	81.61 ± 5.45
	SVM Linear	81.47 ± 2.50	80.59 ± 1.95	80.52 ± 2.28	81.40 ± 1.83
	SVM Polynomial	36.84 ± 0.00	18.42 ± 0.00	26.92 ± 0.00	50.00 ± 0.00
	SVM RBF	79.16 ± 1.87	77.95 ± 1.97	77.36 ± 2.15	77.25 ± 2.45
VGG16	Naive Bayes	64.00 ± 2.09	77.81 ± 4.35	51.25 ± 3.95	57.39 ± 2.46
	MLP	81.26 ± 4.34	82.14 ± 4.67	80.15 ± 4.66	79.66 ± 4.72
	kNN	90.84 ± 1.94	91.54 ± 1.89	90.44 ± 2.08	89.94 ± 2.29
	RF	87.79 ± 1.50	89.65 ± 1.70	87.00 ± 1.65	86.08 ± 1.75
	SVM Linear	86.63 ± 3.71	87.01 ± 3.67	86.16 ± 3.85	86.07 ± 3.84
	SVM Polynomial	57.89 ± 0.00	28.95 ± 0.00	36.67 ± 0.00	50.00 ± 0.00
	SVM RBF	93.37 ± 2.45	94.00 ± 2.16	93.08 ± 2.60	92.64 ± 2.86
VGG19	Naive Bayes	65.11 ± 1.59	77.94 ± 7.05	49.10 ± 2.96	55.40 ± 1.79
	MLP	78.56 ± 5.07	81.53 ± 5.42	74.76 ± 6.80	73.88 ± 6.19
	kNN	91.11 ± 2.72	91.53 ± 3.04	90.51 ± 2.81	89.97 ± 2.66
	RF	86.67 ± 3.51	88.90 ± 3.10	85.04 ± 4.27	83.69 ± 4.35
	SVM Linear	85.44 ± 3.86	84.92 ± 4.11	84.63 ± 4.04	84.56 ± 4.05
	SVM Polynomial	38.89 ± 0.00	19.44 ± 0.00	28.00 ± 0.00	50.00 ± 0.00
	SVM RBF	91.89 ± 2.98	92.56 ± 2.89	91.24 ± 3.30	90.45 ± 3.51
Xception	Naive Bayes	66.00 ± 4.45	63.98 ± 5.23	63.02 ± 4.86	62.88 ± 4.76
	MLP	74.78 ± 4.07	75.45 ± 4.92	71.32 ± 5.30	70.95 ± 5.15
	kNN	88.11 ± 2.54	88.89 ± 3.24	87.11 ± 2.73	86.22 ± 2.72
	RF	88.78 ± 2.96	90.36 ± 3.26	87.66 ± 3.32	86.45 ± 3.31
	SVM Linear	90.78 ± 2.17	91.47 ± 2.52	90.06 ± 2.35	89.23 ± 2.38
	SVM Polynomial	45.56 ± 10.18	22.78 ± 5.09	30.98 ± 4.55	50.00 ± 0.00
	SVM RBF	92.56 ± 2.11	93.35 ± 2.14	91.97 ± 2.31	91.16 ± 2.49

The bold values are mean and standard deviation, respectively. Accuracy, Precision, F1-Score, and Recall obtained through the classification of extracted features.