Search papers, labs, and topics across Lattice.
This study introduces a hybrid deep learning approach that utilizes Mask R-CNN for human subject identification and a color-based algorithm for segmenting exposed skin in images, aimed at enhancing dermal exposure assessment. By analyzing 170 indoor-painting images, the method achieved approximately 80% agreement with human estimates of exposed skin-to-body pixel ratios. This scalable technique not only improves safety assessments but also lays the groundwork for future advancements in body-part recognition and personal protective equipment (PPE) detection.
Achieving 80% agreement with human estimates, this method transforms image analysis into a powerful tool for dermal exposure assessment.
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.
