Somatotype Prediction Using Craniofacial Anthropometry

• Antonio R. A. Brasil UFES
• Patrick M. Ciarelli UFES
• Josinaldo O. Dias UFES

DOI: https://doi.org/10.5753/eries.2025.16032

Abstract

Somatotype is a theory that states that the human body is composed of three main components: endomorph, mesomorph, and ectomorph. It is relevant in the fields of medicine and physical education and is traditionally estimated using measuring equipment applied directly on the body by specialists. This study explored the estimation of somatotype based on craniofacial features extracted from 2D facial images. Eight regression models were evaluated, and the best results were obtained with the SVR model for the endomorph component, kNN for the ectomorph component, and Linear Regression for the mesomorph component. The results can help further studies of facial features as approximate predictors of somatotype.

References

Abràmoff, M. D., Magalhães, P. J., and Ram, S. J. (2004). Image processing with imagej. Biophotonics international, 11(7):36–42.

Akand, M., Civcik, L., Buyukaslan, A., Altintas, E., Kocer, E., Koplay, M., and Erdogru, T. (2019). Feasibility of a novel technique using 3-dimensional modeling and augmented reality for access during percutaneous nephrolithotomy in two different ex-vivo models. International Urology and Nephrology, 51(1):17–25.

Brasil, A. R. A., Amaral, F. T., Oliveira, L. C. S. L., Brasil, G. A., Côco, K. F., and Ciarelli, P. M. (2025). A somatotype classification approach based on generative ai and frontal images of individuals. IEEE Access, pages 1–1.

Brasil, A. R. A., Castro, J. W. B., Gonçalves, E. C., Brasil, G. A., Coco, K. F., and Ciarelli, P. M. (2022). Convolutional neural networks for somatotype classification of images from 3d human bodies. In IX Congresso Latino-Americano de Engenharia Biomédica.

Brasil, A. R. A., de Oliveira Gonçalves, T., Castro, J. W. B., Gonçalves, E. C., Côco, K. F., and Ciarelli, P. M. (2021). Automatic identification of somatotype by digital images. In Simpósio Brasileiro de Automação Inteligente-SBAI, volume 1.

Carter, J. L. and Heath, B. H. (1990). Somatotyping: development and applications, volume 5. Cambridge University Press.

Casadei, K. and Kiel, J. (2019). Anthropometric measurement.

Chiu, C.-Y., Ciems, R., Thelwell, M., Bullas, A., and Choppin, S. (2022). Estimating somatotype from a single-camera 3d body scanning system. European Journal of Sport Science, 22(8):1204–1210.

Dmitrienko, S., Domenyuk, D., Melekhov, S., Domenyuk, S., and Weisheim, L. (2019). Analytical approach within cephalometric studies assessment in people with various somatotypes. Archiv EuroMedica, 9(3):103.

Farkas, L. G., Katic, M. J., Forrest, C. R., and Litsas, L. (2001). Surface anatomy of the face in down’s syndrome: linear and angular measurements in the craniofacial regions. Journal of Craniofacial Surgery, 12(4):373–379.

Fryar, C. D., Carroll, M. D., Gu, Q., Afful, J., and Ogden, C. L. (2021). Anthropometric reference data for children and adults: United states, 2015-2018.

Goncalves, T. d. O. (2017). Identificação do somatotipo de fisiculturistas através de imagens digitais. Master’s thesis, Universidade Federal do Espírito Santo.

Gulsen, A., Okay, C., Aslan, B. I., Uner, O., and Yavuzer, R. (2006). The relationship between craniofacial structures and the nose in anatolian turkish adults: a cephalometric evaluation. American Journal of Orthodontics and Dentofacial Orthopedics, 130(2):131–e15.

Kazemi, V. and Sullivan, J. (2014). One millisecond face alignment with an ensemble of regression trees. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1867–1874.

King, D. E. (2009). Dlib-ml: A machine learning toolkit. The Journal of Machine Learning Research, 10:1755–1758.

Mommaerts, M. and Moerenhout, B. (2011). Ideal proportions in full face front view, contemporary versus antique. Journal of Cranio-Maxillofacial Surgery, 39(2):107–110.

Perissinotto, E., Pisent, C., Sergi, G., Grigoletto, F., Enzi, G., Group, I. W., et al. (2002). Anthropometric measurements in the elderly: age and gender differences. British Journal of nutrition, 87(2):177–186.

Pheasant, S. and Haslegrave, C. M. (2018). Bodyspace: Anthropometry, ergonomics and the design of work. CRC press.

Sagonas, C., Antonakos, E., Tzimiropoulos, G., Zafeiriou, S., and Pantic, M. (2016). 300 faces in-the-wild challenge: Database and results. Image and vision computing, 47:3–18.

Santos, D. A., Dawson, J. A., Matias, C. N., Rocha, P. M., Minderico, C. S., Allison, D. B., Sardinha, L. B., and Silva, A. M. (2014). Reference values for body composition and anthropometric measurements in athletes. PloS one, 9(5):e97846.

Seçgin, Y., Toy, Ş., Şenol, D., and Öner, Z. (2023). Associating craniofacial morphometry determined by photo analysis with somatotype in healthy young individuals. The European Research Journal, 9(4):717–724.

Taylor Jr, H. A., Coady, S. A., Levy, D., Walker, E. R., Vasan, R. S., Liu, J., Akylbekova, E. L., Garrison, R. J., and Fox, C. (2010). Relationships of bmi to cardiovascular risk factors differ by ethnicity. Obesity, 18(8):1638–1645.

Ververs, M.-t., Antierens, A., Sackl, A., Staderini, N., and Captier, V. (2013). Which anthropometric indicators identify a pregnant woman as acutely malnourished and predict adverse birth outcomes in the humanitarian context? PLoS currents, 5:ecurrents–dis.

Yoon, J., Lee, S.-Y., and Lee, J.-Y. (2024). Ai somatotype system using 3d body images: Based on deep-learning and transfer learning. Applied Sciences, 14(6):2608.