176 Int. J. Biometrics, Vol. 10, No. 2, 2018
Copyright © 2018 Inderscience Enterprises Ltd.
New face expression recognition using polar angular
radial transform and principal component analysis
Imène Taleb*, Madani Ould Mammar and
Abdelaziz Ouamri
Department of Electronics,
Faculty of Electrical Engineering,
Université des sciences et de la technologie d’Oran –
Mohamed-Boudiaf, B.P. 1505. El Mnaouer,
Oran, 31000, Algeria
Email: imene.taleb@univ-usto.dz
Email: madani.ouldmammar@univ-mosta.dz
Email: ouamri@yahoo.com
*Corresponding author
Abstract: This paper presents a new method for facial expression recognition
(FER) using a polar mathematical development based on the angular radial
transformation (ART). This method is combined by polar angular radial
transform (P-ART) and principal component analysis (PCA). The new ART is
a powerful descriptor in terms of robustness, description form and way more
information-rich compared to the conventional Cartesian descriptor. Support
vector machine (SVM) training is used to recognise the facial expression for an
input face image. Finally, the experimental results show the performance of the
P-ART and the PCA. The fusion of these two techniques can be better than
other existing methods of recognition of facial expression. During the
experiment, the basis of facial given Japanese female facial expression
(JAFFE) and the Cohn-Kanade databases has been used.
Keywords: facial expression recognition; FER; polar angular radial transform;
P-ART; principal component analysis; PCA; support vector machine; SVM;
fusion; Japanese female expression; JAFFE; Cohn-Kanade.
Reference to this paper should be made as follows: Taleb, I., Mammar, M.O.
and Ouamri, A. (2018) ‘New face expression recognition using polar angular
radial transform and principal component analysis’, Int. J. Biometrics, Vol. 10,
No. 2, pp.176–194.
Biographical notes: Imène Taleb received her Master’s (first-class honours) in
Electronic and Communication from the University of Sciences and
Technologies MB, Oran, Algeria in 2011. She is currently pursuing her PhD in
the Department of Electronic, USTO-MB, Algeria. Since December 2014, she
has been a Research Engineer at the Satellite Development Centre, Oran,
Algeria. He is a member of optical and radar detection team, her research
interests include diverse area of image processing, biometric and computer
vision.
Madani Ould Mammar received his Master’s (DES) in Mathematics from the
University of Oran in 1975, Master’s in EEA from the University of Caen,
France in 1978 and Doctorate in Cycle in Control Theory from the University
of Compiegne, France in 1981 and Doctorate d’Etat in Applied Inverse
Problems from the University of Science and Technology Oran, Algeria in