Yonsei Stress Image Database

YonseiStressImageDatabase is a database built for image-based stress recognition research. We designed an experimental scenario consisting of steps that cause or do not cause stress; Native Language Script Reading, Native Language Interview, Non-native Language Script Reading, Non-native Language Interview. And during the experiment, the subjects were photographed with Kinect v2. This database consists of 50 subjects and 2,020,556 data. Due to the privacy problem, the original image cannot be disclosed but is disclosed in the form of feature maps obtained by passing through the network. The network used to extract the feature map is ResNet-18, and feature maps after the 3rd block out of a total of 4 blocks have been disclosed. The input to the network is a 112×112×3 face RGB image and the size of the feature maps is 7×7×256 (height×width×channel). In the case 'Non-native_Language_Interview' data of subject 26, it was not acquired due to equipment problems.