Using Artificial Intelligence to Quantify Sexual Dimorphism in Aesthetic Faces: Analysis of 100 Facial Points in 42 Caucasian Celebrities

Artificial Intelligence Versus Human Focus Group Rating of Facial Attractiveness

Background: Many open-access artificial intelligence (AI)-based websites that rate facial attractiveness are available, but none have been compared with human focus group outcomes. Objective: To compare human and AI-based websites scoring of facial attractiveness of adult female white faces. Methods: A 40-photograph database of AI-generated adult, white, female, expressionless, and frontal-view facial images were scored by otolaryngology residents and five AI-based facial rating websites: prettyscale.com, attractivenesstest.com, face-score.com/en, hotchat3000.com, and beautyscoretest.com. Sample t-test and bivariate correlation were performed for statistical analyses. Results: The focus group of 24 otolaryngology residents consisted of 62.5% males and 58.3% white participants. There was a strong positive correlation between average human score and average AI score for each photo (Pearson's correlation 0.84, p < 0.01). The average human raters' scores were significantly lower than the average AI scores (5.0 ± 1.8 vs. 6.9 ± 0.9, p < 0.01). Thirty images (75.0%) had statistically higher scores from the AI websites versus the focus group. On correlation analysis, all AI-based websites individually had scores that positively correlate with the human scores (all p < 0.05). Conclusion: AI-based websites and human focus-group scoring of facial attractiveness of adult white female faces were significantly correlated with the AI ratings biased toward higher values, encouraging their cautious utilization in future research.

Analysis of Sexual Dimorphic Features of the Jawline and Chin in White Celebrity Faces

BACKGROUND

The jawline greatly influences facial shape and contributes to facial dimorphism. Analysis of lower facial shape and sexual dimorphic differences in contemporary attractive white faces can advance the goals of lower facial aesthetics and facial gender-affirming surgery (FGAS).

METHODS

Full-face, front-view photos of 47 white female and 21 white male celebrities were included from a list generated using GQ magazine's Highest Paid Models issue, People Magazine's Beautiful issue (1991-2022), and celebrities featured on lifestyle websites. Facial landmarks were detected through a facial analysis program using Vision framework and MATLAB. After converting pixel distances to absolute distances, lower face measurements were compared between males and females.

RESULTS

The mean lower facial height was 6.08 cm in females and 7.00 cm in males (P value<0.001). The mean bigonial width was 11.21 cm in females and 12.30 cm in males (P value<0.001). The ratio of facial height to lower facial height was 2.98 in females and 2.76 in males (P value<0.001), signifying that symmetry in facial thirds is more prevalent in attractive female faces, while a longer lower face is more common in attractive male faces. The greatest differences in female and male facial contours were at gonial angles and chin.

CONCLUSIONS

Analysis of contemporary white celebrity faces demonstrated significantly wider and longer lower facial measurements in males. The overall contour of the female lower face was more tapered at the gonial angles and chin compared to males. These results are important when planning lower facial rejuvenation or FGAS, as lower face size and proportions influence perceived gender and attractiveness.

Facial Morphometrics in Black Celebrities: Contemporary Facial Analysis Using an Artificial Intelligence Platform

The diversity of patients pursuing facial aesthetic and facial gender-affirming surgery (FGAS) is increasing, yet there is a paucity of objective guidelines to facilitate surgical decision-making in patients of color. We conducted a quantitative analysis of black celebrities using standardized frontal photos of 21 female and 21 male celebrities. Celebrities were chosen from popular entertainment magazines and websites, including People Magazine, the Internet Movie Database (IMDb), Cosmopolitan, and Essence. For each celebrity, 100 facial landmarks were detected through a facial analysis artificial intelligence (AI) program. Black males had greater facial height, bizygomatic width, lower facial height, and bigonial width than females. However, the facial height to bigonial width ratio was similar between genders and approximated the golden ratio (1.618). Female faces demonstrated a greater mid-face height to total facial height proportion, and males had a greater lower facial height proportion. Females exhibited an upward-slanted medial brow and shorter total eyebrow length, nose height, and alar width. Forehead height above the lateral brow was greater in males, while central forehead height was similar to females. This is the first study that has utilized AI to provide ethnicity-specific facial morphometrics relevant to facial rejuvenation and FGAS in the black population.