Pain Intensity Estimation by a Self--Taught Selection of Histograms of Topographical Features

TL;DR

This paper introduces Histograms of Topographical features for facial pain intensity estimation, utilizing a semi-supervised self-taught learning approach to improve discrimination and generalization across different individuals.

Contribution

It presents a novel feature extraction method and a self-taught learning procedure for better pain intensity estimation from facial images.

Findings

Enhanced discrimination between pain levels

Improved generalization across subjects

Effective semi-supervised learning approach

Abstract

Pain assessment through observational pain scales is necessary for special categories of patients such as neonates, patients with dementia, critically ill patients, etc. The recently introduced Prkachin-Solomon score allows pain assessment directly from facial images opening the path for multiple assistive applications. In this paper, we introduce the Histograms of Topographical (HoT) features, which are a generalization of the topographical primal sketch, for the description of the face parts contributing to the mentioned score. We propose a semi-supervised, clustering oriented self--taught learning procedure developed on the emotion oriented Cohn-Kanade database. We use this procedure to improve the discrimination between different pain intensity levels and the generalization with respect to the monitored persons, while testing on the UNBC McMaster Shoulder Pain database.