Facial Expression Recognition using Advanced Local Binary Patterns, Tsallis Entropies and Global Appearance Features

Abstract

This paper proposes a novel facial expression recognition approach based on two sets of features extracted from the face images: texture features and global appearance features. The first set is obtained by using the extended local binary patterns in both intensity and gradient maps and computing the Tsallis entropy of the Gabor filtered responses. The second set of features is obtained by performing nullspace based linear discriminant analysis on the training face images. The proposed method is evaluated by extensive experiments on the JAFFE database, and compared with two widely used facial expression recognition approaches. Experimental results show that the proposed approach maintains high recognition rate in a wide range of resolution levels and outperforms the other alternative methods.

The effects of Pose on Facial Expression Recognition

“…This approach is a derivative based LBP which encodes the velocity of local variation. Similar features have been successfully applied to facial expressions recognition [9].…”

“…We attempt to classify each of the prototypical expressions at 5 different yaw angles (0,30,45,60,90). LBPs have yielded accurate results with face recognition [6] and more recently with frontal facial expressions [4,5,9,23]. We apply the LBP operator and its variants to the BU-3DEF database and present our findings.…”

“…Research into facial expression recognition has predominantly been based on near frontal view data [5,9,18]. High recognition rates for these prototypical facial expressions have been recorded in constrained settings.…”

“…This is reflected by current approaches to facial expression recognition, that classify a set of prototypical emotions such as joy, sadness, anger, disgust, surprise and fear [5,9,13]. Many methods for the classification of these prototypical expressions have been presented.…”

An Automated System for Garment Texture Design Class Identification

“…Recently, LBP is considered as an effective texture classification methodology which was proposed for describing the local structure of an image. LBP and its variants can be uniform and/or rotation invariant [21] and have been extensively exploited in many applications, for instance, facial image analysis, including face detection [22][23][24][25], face recognition and facial expression analysis [26][27][28][29][30][31][32][33][34]; demographic (gender, race, age, etc.) classification [35][36][37][38]; moving object detection [39], etc.…”