Subjectivity and complexity of facial attractiveness

Abstract

The origin and meaning of facial beauty represent a longstanding puzzle. Despite the profuse literature devoted to facial attractiveness, its very nature, its determinants and the nature of inter-person differences remain controversial issues. Here we tackle such questions proposing a novel experimental approach in which human subjects, instead of rating natural faces, are allowed to efficiently explore the face-space and “sculpt” their favorite variation of a reference facial image. The results reveal that different subjects prefer distinguishable regions of the face-space, highlighting the essential subjectivity of the phenomenon. The different sculpted facial vectors exhibit strong correlations among pairs of facial distances, characterising the underlying universality and complexity of the cognitive processes, and the relative relevance and robustness of the different facial distances.

Peer Review #1 of "Unsupervised inference approach to facial attractiveness (v0.1)"

“…Generally, males prefer smaller lower face area, higher cheekbones, larger mouths and eyes (see references in Little et al (2011); Rhodes (2006); Thornhill and Gangestad (1999)). These facts are compatible with the results of Ibáñez-Berganza et al (2019). In the present work we go one step further and demonstrate that gender, besides having an impact on the subject-averaged facial sculptures, can actually be predicted with almost certainty for single subjects, based on their facial modifications.…”

“…We remark that the prominent importance of the inter-segment angles i j highlighted in fig. 4-B is fully compatible with the analysis presented in (Ibáñez-Berganza et al (2019)) at the level of the oblique correlation matrix C (xy) , and it goes beyond, as far as it quantitatively assess their relative relevance. As we will see in the next subsection, such information cannot be retrieved from the experimental matrix C only.…”

“…In sec. 3 we analyse the results following our objectives (1,2) described above: we first evaluate the quality of our models as generative models of the set of facial modifications in (Ibáñez-Berganza et al (2019)). Afterwards, we perform a further assessment in which we apply the generative models to the classification of the gender of the subjects from their sculpted facial vectors, and compare the results with that of a purely supervised learning algorithm.…”

“…We analyse the dataset S described by Ibáñez-Berganza et al (2019). In such experiments, each subject was allowed to sculpt her/his favorite deformation of a reference portrait (through the interaction with an software which combines image deformation techniques with a genetic algorithm for the efficient search in the face-space).…”

“…This motivates the search for alternative experimental approaches. Ibáñez-Berganza et al (2019) investigated the question (A) by means of an innovative experimental technique which permits the sampling of a single subject's preferred region in the face-space. 1 As a matter of fact, the method allows the sampling of the subjects' preferred facial modifications with high precision.…”