{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T06:54:34Z","timestamp":1770274474774,"version":"3.49.0"},"reference-count":30,"publisher":"MDPI AG","issue":"23","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Fondation Arts et M\u00e9tiers"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The face blurring of images plays a key role in protecting privacy. However, in computer vision, especially for the human pose estimation task, machine-learning models are currently trained, validated, and tested on original datasets without face blurring. Additionally, the accuracy of human pose estimation is of great importance for kinematic analysis. This analysis is relevant in areas such as occupational safety and clinical gait analysis where privacy is crucial. Therefore, in this study, we explore the impact of face blurring on human pose estimation and the subsequent kinematic analysis. Firstly, we blurred the subjects\u2019 heads in the image dataset. Then we trained our neural networks using the face-blurred and the original unblurred dataset. Subsequently, the performances of the different models, in terms of landmark localization and joint angles, were estimated on blurred and unblurred testing data. Finally, we examined the statistical significance of the effect of face blurring on the kinematic analysis along with the strength of the effect. Our results reveal that the strength of the effect of face blurring was low and within acceptable limits (&lt;1\u00b0). We have thus shown that for human pose estimation, face blurring guarantees subject privacy while not degrading the prediction performance of a deep learning model.<\/jats:p>","DOI":"10.3390\/s22239376","type":"journal-article","created":{"date-parts":[[2022,12,2]],"date-time":"2022-12-02T03:28:04Z","timestamp":1669951684000},"page":"9376","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Effect of Face Blurring on Human Pose Estimation: Ensuring Subject Privacy for Medical and Occupational Health Applications"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3662-1784","authenticated-orcid":false,"given":"Jindong","family":"Jiang","sequence":"first","affiliation":[{"name":"Institut de Biomecanique Humaine Georges Charpak, Arts et Metiers Institute of Technology, 75013 Paris, France"},{"name":"Laboratoire de Conception Fabrication Commande, Arts et Metiers Institute of Technology, 57070 Metz, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wafa","family":"Skalli","sequence":"additional","affiliation":[{"name":"Institut de Biomecanique Humaine Georges Charpak, Arts et Metiers Institute of Technology, 75013 Paris, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Siadat","sequence":"additional","affiliation":[{"name":"Laboratoire de Conception Fabrication Commande, Arts et Metiers Institute of Technology, 57070 Metz, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2775-0106","authenticated-orcid":false,"given":"Laurent","family":"Gajny","sequence":"additional","affiliation":[{"name":"Institut de Biomecanique Humaine Georges Charpak, Arts et Metiers Institute of Technology, 75013 Paris, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,12,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1109\/THMS.2018.2884811","article-title":"Predicting 3-D Lower Back Joint Load in Lifting: A Deep Pose Estimation Approach","volume":"49","author":"Mehrizi","year":"2019","journal-title":"IEEE Trans. Hum. Mach. Syst."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"110086","DOI":"10.1016\/j.jbiomech.2020.110086","article-title":"MOPED25: A multimodal dataset of full-body pose and motion in occupational tasks","volume":"113","author":"Li","year":"2020","journal-title":"J. Biomech."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Haggag, H., Hossny, M., Nahavandi, S., and Creighton, D. (2013, January 10\u201312). Real Time Ergonomic Assessment for Assembly Operations Using Kinect. Proceedings of the 2013 UKSim 15th International Conference on Computer Modelling and Simulation, Cambridge, UK.","DOI":"10.1109\/UKSim.2013.105"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"105485","DOI":"10.1016\/j.cie.2018.10.046","article-title":"Motion Analysis System (MAS) for production and ergonomics assessment in the manufacturing processes","volume":"139","author":"Bortolini","year":"2018","journal-title":"Comput. Ind. Eng."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.gaitpost.2021.03.003","article-title":"A novel dataset and deep learning-based approach for marker-less motion capture during gait","volume":"86","author":"Vafadar","year":"2021","journal-title":"Gait Posture"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1016\/j.gaitpost.2022.03.008","article-title":"Assessment of a novel deep learning-based marker-less motion capture system for gait study","volume":"94","author":"Vafadar","year":"2022","journal-title":"Gait Posture"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1132","DOI":"10.1109\/LRA.2019.2894389","article-title":"Activity Recognition for Ergonomics Assessment of Industrial Tasks with Automatic Feature Selection","volume":"4","author":"Malaise","year":"2019","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/j.apergo.2019.05.004","article-title":"RGB-D ergonomic assessment system of adopted working postures","volume":"80","author":"Abobakr","year":"2019","journal-title":"Appl. Ergon."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"175","DOI":"10.30880\/ijie.2018.10.08.027","article-title":"Usability Study of Integrated RULA-KinectTM System for Work Posture Assessment","volume":"10","author":"Halim","year":"2018","journal-title":"Int. J. Integr. Eng."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"338","DOI":"10.1504\/IJHFMS.2017.087018","article-title":"Usability of corrected Kinect measurement for ergonomic evaluation in constrained environment","volume":"5","author":"Plantard","year":"2017","journal-title":"Int. J. Hum. Factors Model. Simul."},{"key":"ref_11","unstructured":"Yang, K., Yau, J.H., Fei-Fei, L., Deng, J., and Russakovsky, O. (2022, January 17\u201323). A Study of Face Obfuscation in ImageNet. Proceedings of the International Conference on Machine Learning, Baltimore, MD, USA."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Sazonova, N., Schuckers, S., Johnson, P., Lopez-Meyer, P., Sazonov, E., and Hornak, L. (2011, January 13). Impact of out-of-focus blur on iris recognition. Proceedings of the the SPIE Defense, Security, and Sensing, Orlando, FL, USA.","DOI":"10.1117\/12.887052"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Dave, I.R., Chen, C., and Shah, M. (2022, January 18\u201324). SPAct: Self-supervised Privacy Preservation for Action Recognition. Proceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01953"},{"key":"ref_14","unstructured":"Ferrari, V., Hebert, M., Sminchisescu, C., and Weiss, Y. (2018). Learning to Anonymize Faces for Privacy Preserving Action Detection. Computer Vision\u2014ECCV 2018, Springer International Publishing."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zhu, B., Fang, H., Sui, Y., and Li, L. (2020, January 7\u20139). Deepfakes for Medical Video De-Identification: Privacy Protection and Diagnostic Information Preservation. Proceedings of the AAAI\/ACM Conference on AI, Ethics, and Society, New York, NY, USA.","DOI":"10.1145\/3375627.3375849"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Frome, A., Cheung, G., Abdulkader, A., Zennaro, M., Wu, B., Bissacco, A., Adam, H., Neven, H., and Vincent, L. (October, January 27). Large-scale privacy protection in Google Street View. Proceedings of the 2009 IEEE 12th International Conference on Computer Vision, Kyoto, Japan.","DOI":"10.1109\/ICCV.2009.5459413"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Tomei, M., Baraldi, L., Bronzin, S., and Cucchiara, R. (2021, January 19\u201325). Estimating (and fixing) the Effect of Face Obfuscation in Video Recognition. Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Nashville, TN, USA.","DOI":"10.1109\/CVPRW53098.2021.00364"},{"key":"ref_18","unstructured":"Imran, J., Raman, B., and Rajput, A.S. (April, January 30). Robust, efficient and privacy-preserving violent activity recognition in videos. Proceedings of the 35th Annual ACM Symposium on Applied Computing, Brno, Czech Republic."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1515\/cdbme-2022-0028","article-title":"Towards Human Action Recognition during Surgeries using De-identified Video Data: De-identification Prototype for Visual Sensitive Information in the OR","volume":"8","author":"Junger","year":"2022","journal-title":"Curr. Dir. Biomed. Eng."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/j.image.2016.05.020","article-title":"De-identification for privacy protection in multimedia content: A survey","volume":"47","author":"Ribaric","year":"2016","journal-title":"Signal Process. Image Commun."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Fan, L. (2019, January 8\u201312). Practical Image Obfuscation with Provable Privacy. Proceedings of the 2019 IEEE International Conference on Multimedia and Expo (ICME), Shanghai, China.","DOI":"10.1109\/ICME.2019.00140"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009, January 20\u201325). ImageNet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1080\/10255842.2010.540758","article-title":"Fast 3D reconstruction of the lower limb using a parametric model and statistical inferences and clinical measurements calculation from biplanar X-rays","volume":"15","author":"Chaibi","year":"2012","journal-title":"Comput. Methods Biomech. Biomed. Engin."},{"key":"ref_24","unstructured":"(2021, December 20). OpenCV. Available online: https:\/\/docs.opencv.org\/4.x\/d4\/d86\/group__imgproc__filter.html#gac05a120c1ae92a6060dd0db190a61afa."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Iskakov, K., Burkov, E., Lempitsky, V., and Malkov, Y. (November, January 27). Learnable Triangulation of Human Pose. Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.","DOI":"10.1109\/ICCV.2019.00781"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","article-title":"Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments","volume":"36","author":"Ionescu","year":"2014","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"562","DOI":"10.1016\/j.apergo.2016.10.015","article-title":"Validation of an ergonomic assessment method using Kinect data in real workplace conditions","volume":"65","author":"Plantard","year":"2017","journal-title":"Appl. Ergon."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"S3","DOI":"10.1016\/j.clinbiomech.2005.09.007","article-title":"Rotation sequence as an important factor in shoulder kinematics","volume":"21","year":"2006","journal-title":"Clin. Biomech."},{"key":"ref_29","unstructured":"Zheng, C., Wu, W., Yang, T., Zhu, S., Chen, C., Liu, R., Shen, J., Kehtarnavaz, N., and Shah, M. (2021). Deep Learning-Based Human Pose Estimation: A Survey. arXiv, arXiv201213392."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1016\/j.gaitpost.2008.09.003","article-title":"The reliability of three-dimensional kinematic gait measurements: A systematic review","volume":"29","author":"McGinley","year":"2009","journal-title":"Gait Posture"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/23\/9376\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:32:06Z","timestamp":1760146326000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/23\/9376"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,1]]},"references-count":30,"journal-issue":{"issue":"23","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["s22239376"],"URL":"https:\/\/doi.org\/10.3390\/s22239376","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,1]]}}}