Pain intensity recognition via multi‐scale deep network

• DOI: 10.1049/iet-ipr.2019.1448
• Publication Date: 2020-04-03T02:19:27Z
• Authors: Xianlin Peng; Dong Huang; Haixi Zhang
• Keywords: Intensity

Similar to the basic facial expression recognition, one challenge for pain intensity recognition is some individual characteristics, e.g. face shapes, may cause great diversities in same emotion. So it usually very difficult distinguish two adjacent levels of as each has a large variation. In this study, coarse‐to‐fine combination method proposed recognition. The results multi‐scale outputs from multiple base deep network are combined probabilistic way improving discrimination between visually similar levels. A two‐layer tree classifier multi‐task framework well shape replacing planar Softmax network. first layer classifier, classifiers constructed recognizing intensities and conventional second layer. Finally, including jointly optimised during training phase only high level used recognising test phase. extensive experiments on UNBC shoulder dataset show gets promising