Boosting 3D-Geometric Features for Efficient Face Recognition and Gender Classification

Lahoucine Ballihi (1, 2) , Boulbaba Ben Amor (1, 3) , Mohamed Daoudi (1, 3) , Anuj Srivastava (4) , Driss Aboutajdine (2)

1 LIFL - FOX MIIRE
2 GSCM-LRIT - Laboratoire de Recherche en Informatique et Télécommunications [Rabat]
3 Institut TELECOM/TELECOM Lille1
4 Department of Statistics [Tallahassee, FL]

We utilize ideas from two growing but disparate ideas in computer vision -- shape analysis using tools from differential geometry and feature selection using machine learning -- to select and highlight salient geometrical facial features that contribute most in 3D face recognition and gender classification. Firstly, a large set of geometries curve features are extracted using level sets (circular curves) and streamlines (radial curves) of the Euclidean distance functions of the facial surface; together they approximate facial surfaces with arbitrarily high accuracy. Then, we use the well-known Adaboost algorithm for feature selection from this large set and derive a composite classifier that achieves high performance with a minimal set of features. This greatly reduced set, consisting of some level curves on the nose and some radial curves in the forehead and cheeks regions, provides a very compact signature of a 3D face and a fast classification algorithm for face recognition and gender selection. It is also efficient in terms of data storage and transmission costs. Experimental results, carried out using the FRGCv2 dataset, yield a rank-1 face recognition rate of 98% and a gender classification rate of 86%.

Mots clés: Face recognition; gender classification; geodesic path; facial curves; machine learning; feature selection

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Lahoucine Ballihi, Boulbaba Ben Amor, Mohamed Daoudi, Anuj Srivastava, Driss Aboutajdine. Boosting 3D-Geometric Features for Efficient Face Recognition and Gender Classification. IEEE Transactions on Information Forensics and Security, 2012, 7 (6), pp.1766 -1779. ⟨10.1109/TIFS.2012.2209876⟩. ⟨hal-00726088v2⟩