AI-Enhanced System for Lower-Limb Morphology Identification Based on 3D Anthropometric Data

Authors: Aosi Wang, Zhonghao Li, Qian Zhang, Rong Liu

Abstract:

This study presented an artificial intelligence (AI)-enhanced anthropometric identification (AIeAI) system for identifying individuals’ lower-limb shapes and sizes that empowers users in the selection of their fitted legwear and aids manufacturers in devising prototypes in development, thereby cost-effectively and rapidly catering to clothing wearing references. Key anthropometric features were extracted using a combination of support vector machine recursive feature elimination (SVM-RFE) and empirical analysis, with model parameters optimized through grid search, genetic algorithm, and particle swarm optimization. The AIeAI system provides a digital solution for consumers to receive personalized size recommendations and enables manufacturers to develop anthropometric databases for rapid, cost-effective product development tailored to target markets.

Keywords: Body shape and size, feature selection, anthropometric identification, artificial intelligence.

References:

[1] Qian, X., and Yan, B., A study on the detailed classification of human body types based on 3D anthropometric measurements. Journal of Textile Research, 2011. 32(2): p. 107-111.
[2] Cai, X., B. Gu, and H. He, Classification analysis of young female students’ waist–abdomen–hip based on body photos. Textile Research Journal, 2021. 91(11-12): p. 1409-1418.
[3] Yu, J. and J. Li, Classification of young women’s somatotypes in eastern China. J Textile Res, 2020. 41(5): p. 134-139.
[4] Sarakon, P., T. Charoenpong, and S. Charoensiriwath. Face shape classification from 3D human data by using SVM. In The 7th 2014 Biomedical Engineering International Conference. 2014. IEEE.
[5] Jie, Z. and M. Qian, Classification and judgment of boys’ body types based on improved fast search and density peak clustering algorithms. Journal of Textile Research, 2020.
[6] Choi, Y.L. and Y.J. Nam, Classification of upper lateral body shapes for the apparel industry. Human Factors and Ergonomics in Manufacturing & Service Industries, 2010. 20(5): p. 378-390.
[7] Hu, Y., Y. Xia, and B. Gu, An image-based shape analysis approach and its application to young women’s waist-hip-leg position. Ergonomics, 2023. 66(12): p. 2074-2090.
[8] Liu, K., Wang, J.P., Tao X.Y., Zeng, X.Y., Bruniaux, P., Kamalha, E., Fuzzy classification of young women's lower body based on anthropometric measurement. International Journal of Industrial Ergonomics, 2016. 55: p. 60-68.
[9] Wang, J., Li, X.J., Pan, L., Zhang, C.Y., Parametric 3D modeling of young women's lower bodies based on shape classification. International Journal of Industrial Ergonomics, 2021. 84: p. 103142.
[10] Song, H.K. and S.P. Ashdown, Categorization of lower body shapes for adult females based on multiple view analysis. Textile Research Journal, 2011. 81(9): p. 914-931.
[11] Wang, J., X. Li, and Pan, L., Waist hip somatotype and classification of young women in Northeast China. J. Text. Res, 2018. 39(4): p. 106-110.
[12] Wang, H., Sun, S., Cheng, Y., Yao, H., and Wang, J., Study on body characteristics and lower body type classification of adult males in the Jiangnan region. Journal of Textile Universities, 2021. 34(1).
[13] F. Wang, G.W., T. Huang, X. Zhang, and Y. Wang, Female leg type classification driven by front and side morphological features. Journal of Textile Research, 2022. 43(9): p. 188-194.
[14] Mao, Q., Liu, R., Lv, J.Y., Gheerawo, R., A new shape clustered leg sizing system for mass customization fit of compression garment. Fashion and Textiles, 2025. 12(13), https://doi.org/10.1186/s40691-025-00418-x.
[15] Liu, R., Guo, X., Peng, Q., Zhang, L., Lao, T. T., Little, T., Liu, J., Chan, E. Stratified body shape-driven sizing system via three-dimensional digital anthropometry for compression textiles of lower extremities. Textile Research Journal, 2018. 88(18): p.2055–2075.
[16] Blaylock, B.K., Horel, J.D., Liston, S.T., Cloud archiving and data mining of High-Resolution Rapid Refresh forecast model output. Computers & Geosciences, 2017. 109: p. 43-50.
[17] Spetale, F.E., Bulacio, P., Guillaume, S., Murillo, J., Tapia, E., A spectral envelope approach towards effective SVM-RFE on infrared data. Pattern Recognition Letters, 2016. 71: p. 59-65.
[18] Tosin, M.C., Majolo, M., Chedid, R., Cene, V.H., Balbinot, A., sEMG feature selection and classification using SVM-RFE. in 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). 2017. IEEE.
[19] Pino, R., R. Mendoza, and R. Sambayan, A Baybayin word recognition system. PeerJ Computer Science, 2021. 7: p. e596.
[20] Wang, S., Pan, B., Chen, H., Ji, Q., Thermal augmented expression recognition. IEEE transactions on cybernetics, 2018. 48(7): p. 2203-2214.
[21] Luo, J.H. and C.H. Lin, Pure FPGA implementation of an HOG based real-time pedestrian detection system. Sensors, 2018. 18(4): p. 1174.
[22] Phan, A.V., M.L. Nguyen, and L.T. Bui, Feature weighting and SVM parameters optimization based on genetic algorithms for classification problems. Applied Intelligence, 2017. 46: p. 455-469.
[23] Huang, W., Liu, H., Zhang, Y., Mi, R., Tong C., Xiao, W., Shuai, B., Railway dangerous goods transportation system risk identification: Comparisons among SVM, PSO-SVM, GA-SVM and GS-SVM. Applied Soft Computing, 2021. 109: p. 107541.