An unbiased artificial referee in beauty contests based on pattern recognition and AI

Beauty contests have long been popular, but concerns about fairness and bias in judgment have emerged. To address this, integrating artificial intelligence (AI) and pattern recognition (PR) as an unbiased referee shows promise. This paper aims to assess the significance of different facial features, including eyes, nose, lips, chin, eyebrows, and jaws, as well as the role of angles and geometric facial measurements, such as distances between facial landmarks and ratios, in the context of beauty assessment. This study also employs two techniques, namely Principal Component Analysis (PCA) and stacked regression, to predict the attractiveness of faces. The experimental data set used for evaluation is the SCUT-FBP benchmark database. The obtained results, indicated by Mean Absolute Errors (MAE) and Pearson's Correlation Coefficient (PCC), demonstrate the high accuracy of our attractiveness prediction model. This research contributes to the advancement of automatic facial beauty analysis and its practical implications. Furthermore, our results surpass those published recently, further validating the effectiveness of our approach.