Work

Fusing Deep Learned and Hand-Crafted Features of Appearance, Shape, and Dynamics for Automatic Pain Estimation

Year: 2017

Type: conference-paper

Abstract: Automatic continuous time, continuous value assessment of a patient's pain from face video is highly sought after by the medical profession. Despite the recent advances in deep learning that attain impressive results in many domains, pain estimation risks not being able to benefit from this due to the difficulty in obtaining data sets of considerable size. In this work we propose a combination of hand-crafted and deep-learned features that makes the most of deep learning techniques in small sample settings. Encoding shape, appearance, and dynamics, our method significantly outperforms the current state of the art, attaining a RMSE error of less than 1 point on a 16-level pain scale, whilst simultaneously scoring a 67.3% Pearson correlation coefficient between our predicted pain level time series and the ground truth.

Source: International Conference on Automatic Face and Gesture Recognition

DOI: 10.1109/fg.2017.87

Authors: Joy Egede, Michel Valstar, Brais Martinez

Institutions: University of Nottingham Ningbo China, University of Nottingham

Language: English

Topic: Emotion and Mood Recognition

Subfield: Experimental and Cognitive Psychology

Field: Psychology

Domain: Social Sciences

SDG: Good health and well-being

Open Access status: green

Funders: European Commission, Ningbo Municipal Bureau of Science and Technology, Ningbo Municipal Bureau of Education