Sweat Droplets Detection Using Deep Learning for the Impression Mold Technique to Evaluate Sweating Responses to Thermal Stimulus

In this paper, we propose a method for automatically detecting sweat droplets from images taken by replicas of the silicone skin surface created by the Impression Mold Technique (IMT) to evaluate sweating responses to thermal stimulus. The proposed method is a U-Net based segmentation using deep learning. From experimental results, we succeeded in obtaining a result close to the expert's manual identification result of sweat droplets.