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

Table 7

Ablation study of MAE and MSE score for various models.

S. No.	Features used	MAE of SFS for				MSE score of SFS for
		LR	KNN	RF	ANN	LR	KNN	RF	ANN
1.	Without	0.35	0.35	0.37	0.36	0.20	0.17	0.20	0.20
2.	T + C + S	0.30	0.28	0.29	0.31	0.15	0.09	0.11	0.15
3.	T + C	0.31	0.30	0.30	0.33	0.16	0.12	0.12	0.16
4.	T + S	0.32	0.32	0.31	0.35	0.18	0.11	0.12	0.17
5.	C + S	0.31	0.31	0.30	0.33	0.17	0.11	0.11	0.15
6.	T	0.33	0.31	0.35	0.35	0.16	0.15	0.15	0.18
7.	C	0.32	0.34	0.32	0.34	0.15	0.16	0.13	0.17
8.	S	0.34	0.33	0.334	0.33	0.19	0.14	0.17	0.18