Hybrid deep learning quantifies dermal exposure from images

Researchers have developed a hybrid deep learning approach to quantify dermal exposure from images, utilizing Mask R-CNN for subject identification and a color-based algorithm for skin segmentation. This method achieved approximately 80% agreement with human estimates when analyzing 170 indoor-painting images. The system offers a scalable solution for extracting semi-quantitative exposure data and has potential for future enhancements like body-part recognition and PPE detection. AI

IMPACT This method could enable more scalable and objective assessment of occupational exposure risks in various industries.

RANK_REASON The cluster contains a single academic paper detailing a new research methodology. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• Mask R-CNN

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →