A Picture Says Thousands of Words - Harnessing Dermal Exposure Data from Images through Hybrid Deep Learning for Enhanced Safety Assessment
Quick Answer
This study presents a hybrid deep learning approach using Mask R-CNN to quantify dermal exposure from images, achieving 80% agreement with human estimates.
Quick Take
The method processes 170 indoor-painting images to segment exposed skin, paving the way for scalable exposure assessments and potential applications in PPE detection and video analysis.
Key Points
- Hybrid method combines Mask R-CNN and color-based algorithms for skin exposure assessment.
- Achieved approximately 80% agreement with human estimates on exposed skin ratios.
- Utilized 170 images from indoor painting scenarios for model training.
- Future work includes body-part recognition and video-based exposure analysis.
- Demonstrates a scalable approach to semi-quantitative exposure information extraction.
Paper Resources
📖 Reader Mode
~2 min readAbstract:This study developed a hybrid computer vision method to quantify exposed skin from images for dermal exposure assessment. Using 170 indoor-painting images, Mask R-CNN first identified human subjects and removed background interference; a color-based algorithm then segmented exposed skin. The resulting exposed-skin-to-body pixel ratios showed approximately 80% agreement with human estimates. The approach demonstrates a scalable way to extract semi-quantitative exposure information from images, with future extensions to body-part recognition, PPE detection, and video-based exposure analysis.
| Comments: | 3 pages, 2 figures |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| ACM classes: | I.2.10; I.4.6; I.5.4 |
| Cite as: | arXiv:2607.26170 [cs.CV] |
| (or arXiv:2607.26170v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2607.26170 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | The Synergist, October 2024 |
Submission history
From: Haining Zheng [view email]
[v1]
Tue, 28 Jul 2026 18:20:20 UTC (618 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities
ProMoE-FL introduces a Prototype-conditioned Mixture-of-Experts framework for multimodal federated learning, effectively addressing missing modalities. It outperforms existing methods on four chest X-ray datasets, demonstrating superior feature synthesis capabilities in both homogeneous and heterogeneous settings.