Camera-Based Smart Mirror with Machine Learning for Postural Analysis: System Development and Reliability Evaluation

Authors

DOI:

https://doi.org/10.26877/asset.v8i3.3097

Keywords:

computer vision system, digital health, camera-based sensing, machine learning

Abstract

Early postural assessment using camera-based systems remains technically challenging due to variability in user positioning and limited evaluation of measurement repeatability. This study presents the development and repeatability evaluation of a smart mirror system for automated postural analysis using pretrained pose estimation and rule-based geometric classification. The system consists of a fixed camera mounted above a mirror and a connected computing device for real-time processing and visual feedback. Anatomical landmarks were detected from standardized anterior, posterior, and lateral views using an AI-based pose estimation model, and postural asymmetry was quantified using bilateral distance ratios and angular deviation thresholds derived from literature. Reliability was evaluated through repeated measurements to assess the consistency of landmark detection and postural classification outputs. Forty adolescents (age 12.8 ± 0.56 years; 28 males, 12 females) participated in present study. The system intra-rater reliability was evaluated by calculating Intraclass Correlation Coefficients (ICC) for the landmark data and Cohen's Kappa for posture classifications. The system demonstrated excellent reliability for key landmarks in scapula (ICC = 0.98, 95%CI 0.97-0.99) and hip-knee-ankle (ICC = 0.98, 95%CI 0.98-0.99). The classifications for scoliosis assessment also showed excellent agreement (κ = 0.90). These results indicate that the proposed system can produce repeatable posture measurements under controlled conditions; however, this study evaluates repeatability only and does not assess diagnostic accuracy or clinical validity. Further validation against clinical reference standards is required before broader application. 

Author Biographies

  • Fitri Yani, Universitas Aisyiyah Yogyakarta

    Faculty of Health Sciences, Aisyiyah Yogyakarta University, Jl. Siliwangi No.63, Sleman 55292, Daerah Istimewa Yogyakarta, Indonesia

  • Yoga Sahria, Universitas Negeri Yogyakarta

    Graduate School, Yogyakarta State University, Jl. Colombo No.1, Sleman 55281, Daerah Istimewa Yogyakarta, Indonesia

  • Siti Nadhir Ollin Norlinta, Universitas Aisyiyah Yogyakarta

    Faculty of Health Sciences, Aisyiyah Yogyakarta University, Jl. Siliwangi No.63, Sleman 55292, Daerah Istimewa Yogyakarta, Indonesia

  • Riska Risty Wardhani, Universitas Aisyiyah Yogyakarta

    Faculty of Health Sciences, Aisyiyah Yogyakarta University, Jl. Siliwangi No.63, Sleman 55292, Daerah Istimewa Yogyakarta, Indonesia

References

[1] Dop D, Pădureanu V, Pădureanu R, Niculescu SA, Drăgoescu AN, Moroșanu A, et al. Risk factors involved in postural disorders in children and adolescents. life. Life 2024;14:1463. https://doi.org/10.3390/LIFE14111463

[2] Mei Y, Lin YF, Gong Z, Yan B, Liang Q. Prevalence of incorrect posture among school adolescents after the COVID-19 pandemic: a large population-based scoliosis screening in China. Journal of Orthopaedic Surgery and Research 2025 20:1 2025;20:1–12. https://doi.org/10.1186/S13018-025-05479-8

[3] Nnadi C, Fairbank J. Scoliosis: a review. Paediatr Child Health 2010;20:215–20. https://doi.org/10.1016/J.PAED.2009.11.009

[4] Lacroix M, Khalifé M, Ferrero E, Clément O, Nguyen C, Feydy A. Scoliosis. Semin Musculoskelet Radiol 2023;27:529–44. https://doi.org/10.1055/S-0043-1772168/ID/JR2300041-25/BIB

[5] Li M, Nie Q, Liu J, Jiang Z. Prevalence of scoliosis in children and adolescents: a systematic review and meta-analysis. Front Pediatr 2024;12:1399049. https://doi.org/10.3389/FPED.2024.1399049/FULL

[6] Weiss HR, Karavidas N, Moramarco M, Moramarco K. Long-term effects of untreated adolescent idiopathic scoliosis: a review of the literature. Asian Spine J 2016;10:1163. https://doi.org/10.4184/ASJ.2016.10.6.1163

[7] Baranowska A, Sierakowska M, Owczarczuk A, Olejnik BJ, Lankau A, Baranowski P. An analysis of the risk factors for postural defects among early school-aged children. J Clin Med 2023;12:4621. https://doi.org/10.3390/JCM12144621

[8] Kotwicki T. Evaluation of scoliosis today: examination, x-rays and beyond. Disabil Rehabil 2008;30:742–51. https://doi.org/10.1080/09638280801889519

[9] Pjanić S, Talić G, Jevtić N, Golić F, Soldatović I, Chockalingam N. Ultrasound vs. x-ray: a new way for clinicians to track scoliosis progression? Eur J Transl Myol 2025;35:13422. https://doi.org/10.4081/EJTM.2025.13422

[10] Sabirin J, Bakri R, Buang SN, Abdullah AT, Shapie A. School scoliosis screening programme-a systematic review. Med J Malaysia 2010;65:261–7

[11] Ramadhani AN, Romadhoni DL. Pelatihan deteksi dini dan program school exercise sebagai upaya pencegahan adolescent idiopathic scoliosis. Jurnal Abdimas Indonesia 2025;5:395–402. https://doi.org/10.34697/JAI.V5I1.1346

[12] Altaf F, Drinkwater J, Phan K, Cree AK. Systematic review of school scoliosis screening. Spine Deform 2017;5:303–9. https://doi.org/10.1016/J.JSPD.2017.03.009

[13] Grünwald ATD, Roy S, Lampe R. Scoliosis assessment tools to reduce follow-up x-rays. J Orthop Translat 2023;38:12–22. https://doi.org/10.1016/J.JOT.2022.07.010

[14] Kusumo H, Dian Marlina, Achmad Solechan. Sustainable Digital Transformation in Healthcare: Challenges and Directions in the Society 5.0 Era. Advance Sustainable Science Engineering and Technology 2025;7:0250113. https://doi.org/10.26877/asset.v6i4.876

[15] Moreira R, Teles A, Fialho R, Baluz R, Santos TC, Goulart-Filho R, et al. Mobile applications for assessing human posture: a systematic literature review. Electronics 2020, Vol 9, Page 1196 2020;9:1196. https://doi.org/10.3390/ELECTRONICS9081196

[16] Ferrero A, Lambert G, Caretto F, Trucco M, Piano L, Chiarotto A. Effectiveness of mobile apps in the rehabilitation of patients with low back pain. A systematic review with meta-analysis of randomized controlled trials. Arch Phys Med Rehabil 2025. https://doi.org/10.1016/J.APMR.2025.08.023

[17] Hopkins BB, Vehrs PR, Fellingham GW, George JD, Hager R, Ridge ST. Validity and Reliability of Standing Posture Measurements Using a Mobile Application. J Manipulative Physiol Ther 2019;42:132–40. https://doi.org/10.1016/J.JMPT.2019.02.003.

[18] Baldinger, M., Reimer, L. M., & Senner, V. (2025). Influence of the Camera Viewing Angle on OpenPose Validity in Motion Analysis. Sensors, 25(3), 799. https://doi.org/10.3390/s25030799

[19] Cvetkoska B, Marina N, Bogatinoska DC, Mitreski Z. Smart mirror e-health assistant - posture analyze algorithm proposed model for upright posture. 17th IEEE International Conference on Smart Technologies, EUROCON 2017 - Conference Proceedings 2017:507–12. https://doi.org/10.1109/EUROCON.2017.8011163

[20] Pal S, Sangal V. A real-time AI system for posture detection & monitoring. IOSR J Comput Eng 2025;27:32–6.

[21] Badiola-Bengoa A, Mendez-Zorrilla A. A Systematic Review of the Application of Camera-Based Human Pose Estimation in the Field of Sport and Physical Exercise. Sensors (Basel). 2021 Sep 7;21(18):5996. doi: https://doi.org/10.3390/s21185996. PMID: 34577204; PMCID: PMC8472911.

[22] Knutson GA. Anatomic and functional leg-length inequality: A review and recommendation for clinical decision-making. Chiropr Osteopat. 2005;13:11.

[23] Magee DJ. Orthopedic physical assessment. 6th ed. St. Louis: Elsevier Saunders; 2014.

[24] Banno T, Hasegawa T, Yamato Y, et al. Pelvic obliquity in adolescent idiopathic scoliosis: classification and relationship with lumbar curve and spinal balance. Eur Spine J. 2020;29(2):271–279.

[25] Sharma L, Song J, Dunlop D, Felson D, Lewis CE, Segal N, et al. Varus and valgus alignment and incident and progressive knee osteoarthritis. Ann Rheum Dis. 2010;69(11):1940–5. doi: https://doi.org/10.1136/ard.2010.129742

[26] Nikouei F, Ghandhari H, Ameri E, Mokarami F. Shoulder imbalance in adolescent idiopathic scoliosis: a systematic review of the current state of the art. Arch Bone Jt Surg. 2022;10(12):992–1003. doi: https://doi.org/10.22038/ABJS.2022.64282.3086

[27] Alm M, Gutierrez-Farewik EM, Hultling C, Saraste H. Clinical evaluation of seating in persons with complete thoracic spinal cord injury. Spinal Cord. 2003;41:563–571. doi: https://doi.org/10.1038/sj.sc.3101507

[28] Côté P, Kreitz BG, Cassidy JD, Dzus AK, Martel J. A study of the diagnostic accuracy and reliability of the scoliometer and Adam’s forward bend test. Spine (Phila Pa 1976). 1998;23(7):796–802. doi: https://doi.org/10.1097/00007632-199804010-00011 PMID:9563110.

[29] Yip CH, Chiu TT, Poon AT. The relationship between head posture and severity and disability of patients with neck pain. Man Ther. 2008;13:148–154. doi: 1 https://doi.org/0.1016/j.math.2006.11.002

[30] Timurtaş E, Avcı EE, Mate K, Karabacak N, Polat MG, Demirbüken İ. A mobile application tool for standing posture analysis: development, validity, and reliability. Ir J Med Sci 2021;191:2123. https://doi.org/10.1007/S11845-021-02827-5

[31] Wahlund K, List T, Dworkin SF. Temporomandibular disorders in children and adolescents: reliability of a questionnaire, clinical examination, and diagnosis. J Orofac Pain 1998;12:42–51.

[32] Kim JW, Choi JY, Ha EJ, Choi JH. Human Pose Estimation Using MediaPipe Pose and Optimization Method Based on a Humanoid Model. Applied Sciences 2023, Vol 13, Page 2700 2023;13:2700. https://doi.org/10.3390/APP13042700

[33] Naeemah MR, Kamil M. Advances in Deep Learning for Skin Cancer Diagnosis. Advance Sustainable Science Engineering and Technology 2024;6:02404019. https://doi.org/10.26877/asset.v6i4.1002

[34] Roggio F, Trovato B, Sortino M, Musumeci G. A comprehensive analysis of the machine learning pose estimation models used in human movement and posture analyses: A narrative review. Heliyon 2024;10:e39977. https://doi.org/10.1016/J.HELIYON.2024.E39977

[35] Fischer MCM, Krooß F, Habor J, Radermacher K. A robust method for automatic identification of landmarks on surface models of the pelvis. Scientific Reports 2019 9:1 2019;9:13322-. https://doi.org/10.1038/s41598-019-49573-4

[36] Moon KR, Byon SS, Kim SH, Lee BD. Automated assessment of pelvic radiographs using deep learning: A reliable diagnostic tool for pelvic malalignment. Heliyon 2024;10:e29677. https://doi.org/10.1016/J.HELIYON.2024.E29677

[37] Lafayette TB de G, Kunst VH de L, Melo PV de S, Guedes P de O, Teixeira JMXN, Vasconcelos CR de, et al. Validation of Angle Estimation Based on Body Tracking Data from RGB-D and RGB Cameras for Biomechanical Assessment. Sensors 2023, Vol 23, Page 3 2022;23:3. https://doi.org/10.3390/S23010003

[38] Tharatipyakul A, Srikaewsiew T, Pongnumkul S. Deep learning-based human body pose estimation in providing feedback for physical movement: A review. Heliyon 2024;10:e36589. https://doi.org/10.1016/J.HELIYON.2024.E36589

[39] Ye RZ, Subramanian A, Diedrich D, Lindroth H, Pickering B, Herasevich V. Effects of Image Quality on the Accuracy Human Pose Estimation and Detection of Eye Lid Opening/Closing Using Openpose and DLib. J Imaging. 2022 Dec 19;8(12):330. doi: https://doi.org/10.3390/jimaging8120330 . PMID: 36547495; PMCID: PMC9783075.

[40] Pytel, Rafal & Kayhan, Osman & Gemert, Jan. (2021). Tilting at windmills: Data augmentation for deep pose estimation does not help with occlusions. 10568-10575. https://doi.org/10.1109/ICPR48806.2021.9412475

[41] Gu K, Su B. A study of human pose estimation in low-light environments using YOLOv8 model. Appl Comput Eng. 2024;32:136–142.

[42] Stenum J, Cherry-Allen KM, Pyles CO, Reetzke RD, Vignos MF, Roemmich RT. Applications of pose estimation in human health and performance across the lifespan. Sensors (Basel). 2021;21(21):7315. doi: https://doi.org/10.3390/s21217315

Downloads

Published

2026-06-06

Issue

Vol. 8 No. 3 (2026): May - July

Section

Articles

License

Copyright (c) 2026 Advance Sustainable Science Engineering and Technology

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.