Machine-learning at the service of plastic surgery: A case study evaluating facial attractiveness and emotions using R language

Abstract

Since the plastic surgery should consider that facial impression is always dependent on current facial emotion, it came to be verified how precise classification of facial images into sets of defined facial emotions is.Multivariate regression was performed using R language to identify indicators increasing facial attractiveness after undergoing rhinoplasty. Bayesian naive classifiers, decision trees (CART) and neural networks, respectively, were applied to assign a landmarked facial image data into one of the facial emotions, based on Ekman-Friesen FACS scale.Enlargement of nasolabial and nasofrontal angle within rhinoplasty significantly predicts facial attractiveness increasing (p<0.05). Decision trees showed the geometry of a mouth, then eyebrows and finally eyes affect in this descending order an impact on classified emotion. Neural networks proved the highest accuracy of the classification.Performed machine-learning analyses pointed out which geometric facial features increase facial attractiveness the most and should be consequently treated by plastic surgeries.