Body Mass Index Estimation Based on Height and Weight Using Image Processing
Article Sidebar
Main Article Content
Abstract
Body Mass Index (BMI) is a widely used indicator for evaluating body proportions and individual health status. Traditional measurement methods require direct physical contact and are time-consuming. Previous studies have utilized image-based BMI measurement using controlled backgrounds. However, this limitation restricts their application in real-world settings. Moreover, no studies have combined background-independent segmentation with a camera-parameter-based conversion from pixels to physical units, leaving accurate, background-agnostic BMI estimation an open problem. This research addresses this gap using digital image processing on front-view and side-view human body images. The proposed methods include body segmentation using the U²-Net deep learning model, height estimation using pinhole camera projection approach that accounts for camera parameters (focal length, sensor size, camera distance), and weight estimation based on body volume modeling using an elliptical tube slice geometry. The body is treated as a stack of elliptical cross-sections whose width and depth are read from the front- and side-view silhouettes and summed into a total volume. Calibration and correction factors were determined through numerical optimization to obtain optimal global values. The dataset consists of 120 body images collected from 20 subjects. Experimental results show that the system achieves an accuracy of 96.2% (MAE 6.0 cm, RMSE 7.6 cm, MAPE 3.8%) for height estimation and 82.3% (MAE 9.7 kg, RMSE 13.2 kg, MAPE 17.7%) for weight estimation. BMI category classification accuracy reaches 60%. The use of U²-Net enables body segmentation without requiring a controlled background, making the system more flexible and applicable for real-world environments.
Article Details
Section
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
References
[1] B. N. Achsan et al., “Faktor Risiko Obesitas Dengan Low Back Pain Kronis : Tinjauan Sistematik,” CoMPHI Journal: Community Medicine and Public Health of Indonesia Journal, vol. 4, no. 3, pp. 241–248, 2024, doi: 10.37148/comphijournal.v4i3.188. DOI: https://doi.org/10.37148/comphijournal.v4i3.188
[2] I. Mulyasari, P. Afiatna, S. Maryanto, and A. N. Aryani, “Body Mass Index as Hypertension Predictor: Comparison between World Health Organization and Asia-Pacific Standard,” Amerta Nutrition, vol. 7, no. 2SP, pp. 247–251, 2023, doi: 10.20473/amnt.v7i2SP.2023.247-251. DOI: https://doi.org/10.20473/amnt.v7i2SP.2023.247-251
[3] A. Pratama and Z. Zulfahmidah, “Gambaran Indeks Massa Tubuh (IMT) pada Mahasiswa,” Indonesian Journal of Health, vol. 2, no. 01, pp. 1–7, 2021, doi: 10.33368/inajoh.v2i1.29. DOI: https://doi.org/10.33368/inajoh.v2i1.29
[4] M. Situmorang, “Penentuan Indeks Massa Tubuh (IMT) melalui Pengukuran Berat dan Tinggi Badan Berbasis MikrokontrolerAT89S51 dan PC,” Jurnal Teori Dan Aplikasi Fisika, vol. 03, no. 02, pp. 102–110, 2017.
[5] A. B. Abadi, A. Fadllullah, S. Sumardi, S. Mahdi, and A. N. Juniar, “Perhitungan Indeks Massa Tubuh Less Contact Berbasis Computer Vision dan Regresi Linear,” MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer, vol. 21, no. 3, pp. 629–638, 2022, doi: 10.30812/matrik.v21i3.1512. DOI: https://doi.org/10.30812/matrik.v21i3.1512
[6] N. Umy Habibah, P. A. Rosyady, and R. P. Pribadi, “Analisis Indeks Masa Tubuh Berbasis Citra Digital Menggunakan Metode Body Surface Area,” Jetri : Jurnal Ilmiah Teknik Elektro, vol. 20, no. 2, pp. 135–152, 2023, doi: 10.25105/jetri.v20i2.15398. DOI: https://doi.org/10.25105/jetri.v20i2.15398
[7] S. Aulia, F. E. Satria, and R. D. Atmaja, “Sistem Pengukur Tinggi dan Berat Badan berbasis Morphological Image Processing,” ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika, vol. 6, no. 2, p. 219, 2018, doi: 10.26760/elkomika.v6i2.219. DOI: https://doi.org/10.26760/elkomika.v6i2.219
[8] L. Fu, Y. Zhao, H. Chen, L. Ge, Y. Lu, and H. Zhang, “A survey on large-scale unobtrusive BMI estimation for public health,” High-Confidence Computing, vol. 6, no. 3, p. 100402, Sep. 2026, doi: 10.1016/J.HCC.2026.100402. DOI: https://doi.org/10.1016/j.hcc.2026.100402
[9] X. Qin, Z. Zhang, C. Huang, M. Dehghan, O. R. Zaiane, and M. Jagersand, “U 2 -Net : Going deeper with nested U-structure for salient object detection,” Pattern Recognition, vol. 106, p. 107404, 2020, doi: 10.1016/j.patcog.2020.107404. DOI: https://doi.org/10.1016/j.patcog.2020.107404
[10] M. R. Adrian, A. Albadri, and M. Pratiwi, “Model Deep Learning Berbasis Convolutional Neural Network ( CNN ) untuk Identifikasi Tingkat Kerusakan Jalan di Kota Dumai,” Jurnal Teknologi Komputer Dan Informasi, vol. 13, no. 2, pp. 112–131, 2025, doi: 10.52072/jutekinf.v13i2.1816. DOI: https://doi.org/10.52072/jutekinf.v13i2.1816
[11] E. Jeges, I. Kispál, and Z. Hornák, “Measuring human height using calibrated cameras,” 2008 Conference on Human System Interaction, HSI 2008, pp. 755–760, 2008, doi: 10.1109/HSI.2008.4581536. DOI: https://doi.org/10.1109/HSI.2008.4581536
[12] T. H. Supranata, P. S. S. Davin, D. K. Jeremy, A. E. Pratiwi, and M. Wulandari, “Body weight measurement using image processing based on body surface area and elliptical tube volume,” Proceedings of 2018 10th International Conference on Information Technology and Electrical Engineering: Smart Technology for Better Society, ICITEE 2018, pp. 290–294, 2018, doi: 10.1109/ICITEED.2018.8534735. DOI: https://doi.org/10.1109/ICITEED.2018.8534735
[13] A. Géron, Hands-On Machine Learning with Scikit-Learn , Keras , and TensorFlow, 3rd ed., vol. 3rd Editio. Sebastopol, CA: O’Reilly Media, 2022.
[14] D. Chicco, M. J. Warrens, and G. Jurman, “The coefficient of determination R-squared is more informative than SMAPE , MAE , MAPE , MSE and RMSE in regression analysis evaluation,” PeerJ Computer Science, pp. 1–24, 2021, doi: 10.7717/peerj-cs.623. DOI: https://doi.org/10.7717/peerj-cs.623
[15] F. Rahman, H. Fauzi, T. N. Azhar, N. Ayudina, and R. Dwiatmaja, “Analisa Metode Pengukuran Berat Badan Manusia Dengan Pengolahan Citra,” Teknik, vol. 38, no. 1, p. 35, 2017, doi: 10.14710/teknik.v38i1.12663. DOI: https://doi.org/10.14710/teknik.v38i1.12663
[16] T. R. Adiguna, I. R. Magdalena, and S. Saidah, “Sistem Deteksi Idealitas Berat Badan Secara Real Time Dengan Menggunakan Metode Gray Level Co-Occurance Matrix Dan Body Surface Area Designing of Ideality Weight Detection System in Real Time With Gray Level Co-Occurance Matrix Method and Body Surface Are,” e-Proceeding of Engineering, vol. 5, no. 3, pp. 5562–5570, 2018.
[17] H. Mohammedkhan, H. Fleuren, Ç. Güven, and E. Postma, “Inferring Body Measurements from 2D Images: A Comprehensive Review,” Journal of Imaging, vol. 11, no. 6, pp. 1–27, 2025, doi: 10.3390/jimaging11060205. DOI: https://doi.org/10.3390/jimaging11060205
[18] A. Xu, T. Wang, T. Yang, and K. Hu, “Extracting Multi-Dimensional Features for BMI Estimation Using a Multiplex Network,” Symmetry, vol. 17, no. 6, pp. 1–16, 2025, doi: 10.3390/sym17060877. DOI: https://doi.org/10.3390/sym17060877