Machine Learning-Based Facial Beauty Prediction and Analysis of Frontal Facial Images Using Facial Landmarks and Traditional Image Descriptors

Table 6

Ablation study of PC and R² score for various models

S. No.	Features used	PC of SFS for				R^2 score of SFS for
		LR	KNN	RF	ANN	LR	KNN	RF	ANN
1.	Without	0.58	0.71	0.62	0.58	0.33	0.41	0.33	0.30
2.	T + C + S	0.65	0.78	0.70	0.62	0.40	0.48	0.40	0.36
3.	T + C	0.64	0.76	0.68	0.60	0.39	0.46	0.38	0.35
4.	T + S	0.60	0.75	0.67	0.59	0.37	0.45	0.36	0.33
5.	C + S	0.62	0.74	0.67	0.61	0.38	0.45	0.37	0.34
6.	T	0.59	0.74	0.65	0.58	0.38	0.47	0.34	0.34
7.	C	0.58	0.72	0.63	0.59	0.35	0.42	0.37	0.32
8.	S	0.57	0.73	0.64	0.60	0.34	0.43	0.35	0.31