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

Table 12

Performance of each model according to MAE for 11–25 features.

S. No.	Number of features	LR	KNN	RF	ANN
1.	11	0.3903	0.3876	0.3777	0.3727
2.	12	0.4083	0.3957	0.3914	0.4034
3.	13	0.3753	0.3558	0.4188	0.3964
4.	14	0.3897	0.3504	0.4079	0.3876
5.	15	0.3832	0.3546	0.3844	0.446
6.	16	0.3543	0.3468	0.4193	0.4236
7.	17	0.3521	0.3542	0.3913	0.3572
8.	18	0.3561	0.3667	0.3858	0.4279
9.	19	0.357	0.3749	0.4153	0.361
10.	20	0.3589	0.3725	0.4188	0.3654
11.	21	0.3621	0.3763	0.4103	0.3789
12.	22	0.3652	0.3792	0.4069	0.3625
13.	23	0.3624	0.3824	0.4037	0.3764
14.	24	0.3527	0.3761	0.4152	0.371
15.	25	0.361	0.3601	0.4092	0.3762