Effect of Face Blurring on Human Pose Estimation: Ensuring Subject Privacy for Medical and Occupational Health Applications
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 es...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/23/9376 |
| _version_ | 1797462102924853248 |
|---|---|
| author | Jindong Jiang Wafa Skalli Ali Siadat Laurent Gajny |
| author_facet | Jindong Jiang Wafa Skalli Ali Siadat Laurent Gajny |
| author_sort | Jindong Jiang |
| collection | DOAJ |
| description | 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’ 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 (<1°). 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. |
| first_indexed | 2024-03-09T17:31:44Z |
| format | Article |
| id | doaj.art-37494346cf2b4b39b219c0ed85cfb461 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T17:31:44Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-37494346cf2b4b39b219c0ed85cfb4612023-11-24T12:13:10ZengMDPI AGSensors1424-82202022-12-012223937610.3390/s22239376Effect of Face Blurring on Human Pose Estimation: Ensuring Subject Privacy for Medical and Occupational Health ApplicationsJindong Jiang0Wafa Skalli1Ali Siadat2Laurent Gajny3Institut de Biomecanique Humaine Georges Charpak, Arts et Metiers Institute of Technology, 75013 Paris, FranceInstitut de Biomecanique Humaine Georges Charpak, Arts et Metiers Institute of Technology, 75013 Paris, FranceLaboratoire de Conception Fabrication Commande, Arts et Metiers Institute of Technology, 57070 Metz, FranceInstitut de Biomecanique Humaine Georges Charpak, Arts et Metiers Institute of Technology, 75013 Paris, FranceThe 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’ 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 (<1°). 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.https://www.mdpi.com/1424-8220/22/23/9376face blurringdeep learninghuman pose estimationkinematic analysis |
| spellingShingle | Jindong Jiang Wafa Skalli Ali Siadat Laurent Gajny Effect of Face Blurring on Human Pose Estimation: Ensuring Subject Privacy for Medical and Occupational Health Applications Sensors face blurring deep learning human pose estimation kinematic analysis |
| title | Effect of Face Blurring on Human Pose Estimation: Ensuring Subject Privacy for Medical and Occupational Health Applications |
| title_full | Effect of Face Blurring on Human Pose Estimation: Ensuring Subject Privacy for Medical and Occupational Health Applications |
| title_fullStr | Effect of Face Blurring on Human Pose Estimation: Ensuring Subject Privacy for Medical and Occupational Health Applications |
| title_full_unstemmed | Effect of Face Blurring on Human Pose Estimation: Ensuring Subject Privacy for Medical and Occupational Health Applications |
| title_short | Effect of Face Blurring on Human Pose Estimation: Ensuring Subject Privacy for Medical and Occupational Health Applications |
| title_sort | effect of face blurring on human pose estimation ensuring subject privacy for medical and occupational health applications |
| topic | face blurring deep learning human pose estimation kinematic analysis |
| url | https://www.mdpi.com/1424-8220/22/23/9376 |
| work_keys_str_mv | AT jindongjiang effectoffaceblurringonhumanposeestimationensuringsubjectprivacyformedicalandoccupationalhealthapplications AT wafaskalli effectoffaceblurringonhumanposeestimationensuringsubjectprivacyformedicalandoccupationalhealthapplications AT alisiadat effectoffaceblurringonhumanposeestimationensuringsubjectprivacyformedicalandoccupationalhealthapplications AT laurentgajny effectoffaceblurringonhumanposeestimationensuringsubjectprivacyformedicalandoccupationalhealthapplications |