Detection of confusion behavior using a facial expression based on different classification algorithms

Abstract

Confusion detection systems (CDSs) that need Noninvasive, mobile, andcost-effective methods use facial expressions as a technique to detectconfusion. In previous works, the technology that the system usedrepresents a major gap between this proposed CDS and other systems.This CDS depends on the Facial Action Coding System (FACS) that isused to extract facial features. The FACS shows the motion of the facialmuscles represented by Action Units (AUs); the movement is representedwith one facial muscle or more. Seven AUs are used as possible markersfor detecting confusion that has been implemented in the form of a singlevector of facial action; the AUs that have been used in this work are AUs4, 5, 6, 7, 10, 12, and 23. The database used to calculate the performanceof the proposed CDS is gathered from 120 participants (91males, 29females), between the ages of 18-45. Four types of classificationalgorithms are used as individuals; these classifiers are (VG-RAM),(SVM), Logistic Regression and Quadratic Discriminant classifiers. Thebest success rate was found when using Logistic Regression and QuadraticDiscriminant. This work introduces different classification techniques todetect confusion by collecting an actual database that can be used toevaluate the performance for every CDS employing facial expressions andselecting appropriate facial features