Pain recognition and intensity rating based on Comparative Learning

Automatic pain recognition can improve medical treatment, especially when the patient is not able to utter on his pain experience. Facial expressions with their intensities and dynamics contain valuable information for recognising pain. We propose a concept for distinguishing facial expressions of pain from others and assessing the pain expression intensity. It is based on a Support Vector Machine (SVM) classifier and a function model for intensity rating. The intensity model is trained using Comparative Learning, a new technique that simplifies labelling of the data. Using a database of 3D posed pain sequences we show the suitability of the concept to recognise pain expressions, distinguish different intensities and spot even slight intensity changes in its temporal context.

1. INTRODUCTION

The objective assessment of acute pain is a challenging problem, that has not been solved sufficiently yet. In clinics the common practice is to rely on the utterance of the patient. For mentally affected patients this is little reliable and valid. For non-vigilant people or newborns it cannot be used at all. However, there are characteristic changes in the facial expression that indicate pain and are closely related to the experienced pain severity [1], [2]. But it requires a lot of training to interpret these signals reliably. An objective assessment using the Facial Action Coding System (FACS) [3] needs expert knowledge and much time. Thus, it is not feasible for clinics.