No Detail Found!

Quantitative Assessment of Facial Symmetry: A Standardised Geometric Morphometric Method Using Open-Source Landmark Data

Author(s)
Tianshun Xie Department of Plastic and Cosmetic Surgery, The Fifth Affiliated Hospital of Sun Yat-Sen University, Sun Yat-Sen University, Zhuhai, Guangdong, China
Xinfeng Huang Department of Plastic and Cosmetic Surgery, The Fifth Affiliated Hospital of Sun Yat-Sen University, Sun Yat-Sen University, Zhuhai, Guangdong, China
Abstract
Background: Facial symmetry is a key metric in cosmetic and reconstructive facial assessment. Conventional evaluations rely predominantly on subjective visual judgment, lacking standardized, reproducible quantitative tools. This study aimed to develop an open-source geometric morphometric framework for 2D facial symmetry quantification and explore its association with demographic factors and perceived attractiveness. Methods: In this cross-sectional computational morphometric analysis, we used the public SCUT-FBP5500 dataset containing 5,500 frontal images with manually refined 86point landmarks and attractiveness ratings from 60 independent assessors. A mid-sagittal reference line was estimated and the Geometric Symmetry Index (GSI) was defined as the mean normalized Euclidean distance between bilateral landmarks and their mirrored counterparts. Lower GSI values indicate greater geometric facial symmetry. Sex differences and attractiveness correlations were analysed via Welch's t-test and Spearman's rank correlation. Results: Valid GSI values were obtained for 5,499 subjects (one excluded for incomplete landmarks). The cohort showed generally high facial symmetry. Males exhibited significantly greater asymmetry than females (Cohen's d = 0.58, 95% CI: 0.52-0.63, p < 0.001). GSI had a modest but significant negative correlation with attractiveness ratings (? = -0.277, 95% CI: -0.302 to -0.253, p < 0.001). Conclusion: This interpretable, reproducible open-source framework avoids the black-box limitations of complex AI models, providing a standardized solution for objective facial symmetry measurement. With further clinical validation, it may support aesthetic surgery planning, postoperative outcome assessment and digital patient communication.
Publication Details
Page(s) 193-197
Published Journal: Journal of Pioneering Medical Sciences, Volume: 15, Issue: 6, Year: 2026

Request the full text from PASTIC

Keywords
Facial Attractiveness, Aesthetic Surgery, Quantitative assessment, Geometric morphometry, Facial Landmarks, Facial Symmetry
References
Little A.C. .2010 .. Facial Attractiveness: Evolutionary Based Research.” Philosophical Transactions of the Royal Society B: Biological Sciences, 0404(1571) : 1638-1659.
Foo Y.Z. .2017 .. Predictors of Facial Attractiveness and Health in Humans.” Scientific Reports, 7 : .
Boukhari D.E.,Part A .2025 .A Comprehensive Review of Facial Beauty Prediction Using Deep Learning Techniques. Engineering Applications of Artificial Intelligence, 112009 : .
Liang L. .2018 .SCUT-FBP5500: A Diverse Benchmark Dataset for Multi-Paradigm Facial Beauty Prediction. 2018 24th International Conference on Pattern Recognition, 8545203 : 1598-1603.
Jones A.L.,Jaeger B. .2019 .Biological Bases of Beauty Revisited: The Effect of Symmetry, Averageness and Sexual Dimorphism on Female Facial Attractiveness. ” Symmetry, 11(2) : .
0

Citations

0

Downloads

13

Views