Sélection de caractéristiques géométriques pour la reconnaissance faciale 3D

Sélection de caractéristiques géométriques pour la reconnaissance faciale 3D

Lahoucine Ballihi Boulbaba Ben Amor  Mohamed Daoudi  Anuj Srivastava  Driss Aboutajdine  

LIFL (UMR USTL/CNRS 8022) Université Lille 1 59650 Villeneuve d’Ascq, France

LRIT, Unité Associée au CNRST (URAC 29) Université Mohammed V - Agdal Rabat, Maroc

Institut Mines-Télécom, Télécom Lille 1 Villeneuve d’Ascq, France

Departement of Statistics, Florida State University Tallahassee, FL 32306, USA

Corresponding Author Email: 
lahoucine.ballihi@telecom-lille1.eu
Page: 
383-407
|
DOI: 
https://doi.org/10.3166/TS.29.383-407
Received: 
N/A
| |
Accepted: 
N/A
| | Citation

OPEN ACCESS

Abstract: 

The proposed framework combines machine learning techniques and Riemannian geometry-based shape analysis. We represent facial surfaces by collections of radial curves and iso-level curves, the shapes of corresponding curves are compared using a Riemmannian framework. We select the most discriminative curves using the well known AdaBoost algorithm. The experiment involving FRGC v2 dataset demonstrates the effectiveness of this feature selection by achieving 98.02 % as rank-1 recognition rate.

RÉSUMÉ

Dans cet article nous proposons de coupler la géométrie riemannienne avec les techniques d’apprentissage pour une biométrie faciale efficace et robuste aux changements d’expressions faciales. Nous représentons localement la forme des surfaces faciales par des collections de courbes 3D. Nous appliquons des techniques d’apprentissage afin de déterminer les courbes les plus pertinentes à la reconnaissance d’identité des personnes. Le taux de reconnaissance de l’ordre de 98, 02 % sur le benchmark de référence FRGC v2 confirme l’efficacité de coupler l’analyse géométrique de la forme avec des techniques d’apprentissage.

Keywords: 

geometric features, riemannian geometry, geodesic path, facial curves, AdaBoost

MOTS-CLÉS

géométrie riemannienne, chemin géodésique, courbes faciales, AdaBoost

Extended Abstract
1. Introduction
2. Aperçu De L’approche Proposée
3. Prétraitement Des Scans 3D Et Détection Du Bout Du Nez
4. Extraction Des Courbes Faciales
5. Analyse Riemannienne Des Surfaces Faciales
6. Sélection Des Caractéristiques Géométriques Faciales 3D
7. Résultats Expérimentaux
8. Conclusion Et Perspectives
  References

Ballihi L., Ben Amor B., Daoudi M., Srivastava A., Aboutajdine D. (2011). Selecting 3D curves on the nasal surface using adaboost for person authentication. In Proceedings of the 4th eurographics conference on 3D object retrieval, p. 101-104. Llandudno, UK.

Ballihi L., Ben Amor B., Daoudi M., Srivastava A., Aboutajdine D. (2012, dec.). Boosting 3-D-geometric features for efficient face recognition and gender classification. IEEE Transactions on Information Forensics and Security, vol. 7, no 6, p. 1766-1779.

Ben Hamza A., Luque-Escamilla P. L., Martínez-Aroza J., Román-Roldán R. (1999). Removing noise and preserving details with relaxed median filters. Journal of Mathematical Imaging and Vision, vol. 11, no 2, p. 161-177.

Berretti S., Del Bimbo A., Pala P. (2010). 3D face recognition using isogeodesic stripes. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, no 12, p. 2162-2177.

Besl P. J., McKay N. D. (1992). A method for registration of 3-d shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, no 2, p. 239-256.

Chang K. I., Bowyer K. W., Flynn P. J. (2006). Multiple nose region matching for 3D face recognition under varying facial expression. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no 10, p. 1695–1700.

Cook J. A., Chandran V., Fookes C. B. (2006). 3D face recognition using log-gabor templates. In Bmvc, p. 769-778. Edinborugh, Scotland.

Daniyal F., Nair P., Cavallaro A. (2009, sept.). Compact signatures for 3D face recognition under varying expressions. In Advanced video and signal based surveillance. avss ’09, p. 302-307.

Drira H., Ben Amor B., Srivastava A., Daoudi M. (2009). A riemannian analysis of 3D nose shapes for partial human biometrics. In International conference on computer vision (iccv), p. 2050-2057.

El Oirrak A., Daoudi M., Aboutajdine D. (2002). Affine invariant descriptors using fourier series. Pattern Recognition Letters, vol. 23, no 10, p. 1109-1118.

Faltemier T. C., Bowyer K. W., Flynn P. J. (2008). A region ensemble for 3-d face recognition. IEEE Transactions on Information Forensics and Security, vol. 3, no 1, p. 62-73.

Freund Y., Schapire R. E. (1995). A decision-theoretic generalization of on-line learning and an application to boosting. In Eurocolt ’95: Proceedings of the second european conference on computational learning theory, p. 23–37. London, UK, Springer-Verlag.

Haar F. B. ter, Veltkamp R. C. (2009). A 3D face matching framework for facial curves. Graph. Models, vol. 71, no 2, p. 77–91.

Huang D., Ardabilian M., Wang Y., Chen L. (2011, march). A novel geometric facial representation based on multi-scale extended local binary patterns. In Automatic face gesture recognition and workshops (fg 2011), p. 1-7.

Joshi S. H., Klassen E., Srivastava A., Jermyn I. (2007, June). A novel representation for riemannian analysis of elastic curves in Rn. In Computer vision and pattern recognition (cvpr), p. 1–7.

Kakadiaris I., Passalis G., Toderici G., Murtuza M., Lu. Y. (2007, april). Three-dimensional face recognition in the presence of facial expressions: An annotated deformable model approach. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 29, no 4, p. 640 -649.

Klassen E., Srivastava A. (2006). Geodesics between 3D closed curves using path-straightening. In European conference on computer vision (eccv), p. 95-106.

Klassen E., Srivastava A., Mio W., Joshi S. (2004). Analysis of planar shapes using geodesic paths on shape spaces. IEEE Pattern Analysis and Machine Intelligence, vol. 26, no 3, p. 372-383.

Li X., Jia T., 0002 H. Z. (2009). Expression-insensitive 3D face recognition using sparse representation. In Computer vision and pattern recognition (cvpr), p. 2575-2582.

Mahmoudi S., Daoudi M. (2007). A probabilistic approach for 3d shape retrieval by characteristic views. Pattern Recognition Letters, vol. 28, no 13, p. 1705-1718.

Mian A. S., Bennamoun M., Owens R. A. (2007, nov.). An efficient multimodal 2D-3D hybrid approach to automatic face recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 29, no 11, p. 1927-1943.

Michor P. W., Mumford D. (2006). Riemannian geometries on spaces of plane curves. Journal of the European Mathematical Society, vol. 8, p. 1-48.

Phillips P. J., Flynn P. J., Scruggs W. T., Bowyer K. W., Chang J. (2005). Overview of the face recognition grand challenge. In Computer vision and pattern recognition (cvpr), p. 947-954.

Samir C., Srivastava A., Daoudi M. (2006). Three-dimensional face recognition using shapes of facial curves. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no 11, p. 1847-1857.

Samir C., Srivastava A., Daoudi M., Klassen E. (2009). An intrinsic framework for analysis of facial surfaces. International Journal of Computer Vision, vol. 82, no 1, p. 80-95.

Sebastian T. B., Klein P. N., Kimia B. B. (2003). On aligning curves. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no 1, p. 116-125.

Srivastava A., Klassen E., Joshi S. H., Jermyn I. H. (2011). Shape analysis of elastic curves in euclidean spaces. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, no 7, p. 1415-1428.

Székely G., Kelemen A., Brechbühler C., Gerig G. (1995). Segmentation of 3D objects from mri volume data using constrained elastic deformations of flexible fourier surface models. In Cvrmed, p. 495-505.

Tanaka H. T., Ikeda M., Chiaki H. (1998). Curvature-based face surface recognition using spherical correlation - principal directions for curved object recognition. In International conference on automatic face and gesture recognition, p. 372-377.

Viola P., Jones M. J. (2004). Robust real-time face detection. International Journal of Computer Vision, vol. 57, no 2, p. 137–154.

Wang S., Wang Y., Jin M., Gu X., Samaras D. (2006). 3D surface matching and recognition using conformal geometry. In Computer vision and pattern recognition (cvpr), p. 2453-2460.

Wang Y., Liu J., Tang X. (2010, October). Robust 3D face recognition by local shape difference boosting. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, p. 1858-1870.

Yagou H., Ohtake Y., Belyaev A. G. (2002). Mesh smoothing via mean and median filtering applied to face normals. Proceedings of the geometric modeling and processing, p. 1-24. Washington, DC, USA, IEEE Computer Society.