preview

Automatic Pain Assessment Paper

Satisfactory Essays

\section{Automatic Pain Assessment}
The proposed pain assessment system consists of two main stages: 1) face detection and preprocessing and 2) pain expression recognition. We describe each stage in detail below.

\subsection{Automatic Face Detection and Preprocessing}
We applied ZFace \cite{jeni2015dense}, which is a person-independent tracker, in each video to detect the face and obtain 49 facial landmark points. The tracker outputs the 49 points' coordinates as well as a failure message to indicate the failure frames; those frames were excluded from further analysis. For each frame, we used the detected points to register and crop the infant's exact face region. We applied the tracker in 200 videos to detect the face and the landmark points.

Get Access