Boosting steerable features for 2D face recognition on IV 2 database

Nefissa Khiari Hili (1, 2) , Sylvie Lelandais (1) , Christophe Montagne (1) , Kamel Hamrouni (2)

1 IBISC - Informatique, Biologie Intégrative et Systèmes Complexes
2 LSTS - Laboratoire des Systèmes et du Traitement du Signal [ENIT]

In this paper, a novel approach for 2D face recognition is proposed, based on local feature extraction through a multi-resolution multi-orientation linear method, Steerable Pyramid (SP) and on a feature selection and classification by means of a non-linear method, Adaboost. Many strategies have been elaborated and tested on IV 2 database including challenging variability such as pose, expression, illumination and quality. To show the robustness of the method, it was compared to five algorithms submitted to the first evaluation campaign on 2D face recognition using IV 2 database. Proposed algorithm is almost among the two best ones.

Keywords: 2D face recognition; Adaboost; Feature extraction; Feature selection; Steerable pyramid

Domains: Signal and Image processing; Signal and Image Processing

Nefissa Khiari Hili, Sylvie Lelandais, Christophe Montagne, Kamel Hamrouni. Boosting steerable features for 2D face recognition on IV 2 database. International Conference on Bio-Inspired Systems and Signal Processing (BIOSIGNAL 2012), Feb 2012, Vilamoura, Algarve, Portugal. pp.488--493. ⟨hal-00744921⟩