Research Article
Machine Learning-Based Facial Beauty Prediction and Analysis of Frontal Facial Images Using Facial Landmarks and Traditional Image Descriptors
Table 10
Performance of each model according to R2 Score for 11–25 features.
| S. No. | Number of features | LR | KNN | RF | ANN |
| 1. | 11 | 0.2604 | 0.302 | 0.3344 | 0.2888 | 2. | 12 | 0.1904 | 0.2509 | 0.2402 | 0.203 | 3. | 13 | 0.2331 | 0.3945 | 0.0604 | 0.2264 | 4. | 14 | 0.1892 | 0.4162 | 0.1029 | 0.213 | 5. | 15 | 0.2082 | 0.3753 | 0.2676 | -0.0114 | 6. | 16 | 0.3303 | 0.3787 | -0.003 | 0.0246 | 7. | 17 | 0.3459 | 0.3462 | 0.2165 | 0.3288 | 8. | 18 | 0.3457 | 0.309 | 0.2298 | 0.0178 | 9. | 19 | 0.331 | 0.3952 | 0.1308 | 0.3096 | 10. | 20 | 0.3369 | 0.3924 | 0.1395 | 0.3169 | 11. | 21 | 0.3256 | 0.4021 | 0.1456 | 0.3178 | 12. | 22 | 0.3248 | 0.4089 | 0.1324 | 0.316 | 13. | 23 | 0.331 | 0.4097 | 0.1437 | 0.3099 | 14. | 24 | 0.3358 | 0.3924 | 0.1587 | 0.3184 | 15. | 25 | 0.3294 | 0.3910 | 0.1308 | 0.3269 |
|
|