Development of a Fast Panoramic Face Mosaicing and Recognition System. Développement d’un Système Rapide pour le Mosaïquage et la Reconnaissance de Visages Panoramiques

Development of a Fast Panoramic Face Mosaicing and Recognition System

Développement d’un Système Rapide pour le Mosaïquage et la Reconnaissance de Visages Panoramiques

F. Yang M. Paindavoine  D. Ginhac  J. Dubois 

Laboratoire Le2i,Aile de l’Ingénieur - Mirande Université de Bourgogne, BP 400 - 21011 Dijon cedex

24 January 2005
31 December 2005
| Citation



In this article,we present some development results of a system that performs mosaicing of panoramic faces.Our objective is to study the feasibility of panoramic face construction in real-time.This led us to conceive of a very simple acquisition system composed of 5 standard cameras and 5 face views taken simultaneously at different angles.Then, we chose an easily hardware-achievable algorithm:successive linear transformation,in order to compose a panoramic face of 150° from these 5 views.The method has been tested on hundreds of faces.In order to validate our system of panoramic face mosaicing,we also conducted a preliminary study on panoramic faces recognition,based on the «eigenfaces» method.Experimental results obtained show the feasibility and viability of our system.This allows us to envisage later a hardware implantation.We also are considering applying our system to other applications such as human expression categorization using movement estimation and fast 3D face reconstruction.


Dans cet article,nous présentons quelques résultats sur le développement d’un système de mosaïquage de visages panoramiques. Notre objectif est d’étudier la faisabilité de construction de visages panoramiques en temps réel. Ceci nous a conduit tout d’abord à concevoir un système d’acquisition très simple,composé de 5 caméras standards qui réalise la prise de 5 vues simultanément sous différents angles. Puis,nous avons choisi un algorithme facilement implantable sur des systèmes embarqués. Cet algorithme est basé sur des transformations linéaires successives,pour composer un visage panoramique de 150° à partir de ces 5 vues. La méthode a été testée sur une centaine de visages. Nous avons aussi effectué une étude préliminaire sur la reconnaissance de visages panoramiques dans le but de valider notre système de mosaïquage de visages. La reconnaissance est basée sur le modèle de «visages propres». Les résultats expérimentaux ont montré la faisabilité et la viabilité du système proposé permettant d’envisager une future implantation matérielle. Nous pensons aussi utiliser notre système de mosaïquage dans d’autres applications comme la reconstruction rapide de visages 3D et la catégorisation des expressions basée sur le mouvement.


Panoramic vision,image mosaicing,face recognition,principal Component Analysis,FFT.

Mots clés 

Vision panoramique,mosaïquage d’images,reconnaissance de visages,analyse en Composantes Principales,FFT.

1. Introduction
2. Présentation du Système d’Acquisition
3. Construction de Visages Panoramiques
4. Reconnaissance des Visages Panoramiques
5. Conclusions et Perspectives

[1] A.J. HOWELL and H. BUXTON, Learning identity with radial basis function networks, Neurocomputing, Vol.20, pp.15-34, 1998. 

[2] T. SIM, R. SUKTHANKAR and al., Memory-Based face recognition for visitor Identification, 4th IEEE International Conf. On automatic face and gesture recognition, Grenoble, France, 26-30 March 2000. 

[3] M. TURK and A. PENTLAND, Eigenfaces for recognition, Journal Cognitive neuroscience, Vol.3, pp.71-86, 1991. 

[4] H. ABDI, D. VALENTIN and A. O’TOOLE, A generalized autoassociator model for face semantic process, in Optimization and neural network, edited by D.Levine (Erlbaum, Hillsdale), 1997. 

[5] M. SLIMANE, T. BROUARD and al., Unsupervised learning of pictures by genetic hibrydization of hidden Markov chain, Signal Processing, Vol.16, No.6, pp.461-475, 1999. 

[6] P.J. PHILLIPS, P. GROTHER and al., Face recognition Vendor Test 2002, IEEE International workshop on Analysis and Modeling of Faces and Gestures (AMFG), 2003. 



[9] F. TSALAKANIDOU, D. TZOVARAS and M.G. STRINTZIS, Use of delth and colour eigenfaces for face recognition, Pattern recognition Letters, Vol.24, pp.1427-1435, 2003. 

[10] C. BEUMIER, M. ACHEROY, Face verification from 3D and grey level clues, Pattern recognition letters, Vol.22, pp.1321-1329, 2001. 

[11] C. HEHSER, A. SRIVASTAVA and G. ERLEBACHER, A nouvel technique for face recognition using range imaging, 7th International Sympoosium on Siganl Processing and its Apllications (ISSPA), 2003. 

[12] X. LU, D. COLBRY and A.K. JAIN, Three-Dimensional model based face recognition, Proc. International Conference on Pattern Recognition, Cambridge, UK, August, 2004. 

[13] K.W. BOWYER, K. CHANG and P. FLYNN, A survey of 3D and multi-modal 3D+2D face recognition, International Conference on Pattern Recognition (ICPR), 2004. 

[14] V. BLANZ and T. VETTER, Face recognition based on fitting a 3D morphable model, IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol.25, pp.1063-1074, September, 2003 

[15] J.G. WANG, R. VENKATESWARLU and E.T. LIM, Face tracking and recognition from stereo sequence, Computer Science, Vol. 2688, pp.145-153, 2003. 

[16] R. HARTLY and A. ZISSERMAN, Multiple View Geometry in Computer vision, Cambridge University Press, Second Edition, 2003. 

[17] X. LIU and T. CHEN, Geometry-assisted statistical modeling for face mosaicing, IEEE International Conference on Image Processing (ICIP), Vol.2, pp.883-886, Barcelona, Spain, 2003. 

[18] F.YANG et M. PAINDAVOINE, Détection et Localisation de Visages dans une Scène : Implantation Parallèle sur un Réseau de DSPs, Revue Traitement du signal. Vol.17, N° 2, 2000. 

[19] F. YANG, M. PAINDAVOINE, N. MALASNÉ, Localisation et Reconnaissance de Visages en temps Réel avec un Réseau de Neurones RBF : Algorithme et Architecture, Revue Traitement du signal. Volume 20, No.4, 2003. 

[20] F. YANG, M. PAINDAVOINE, H. ABDI and J. MITÉRAN, A new filtering technique combining a wavelet transform with a linear neural network: application to face recognition, Optical Engineering SPIE. Vol.39, No.11, 2000.

[21] F. YANG, M. PAINDAVOINE, Implementation of a RBF neural network on embedded systems: Real time face tracking and identity verification, IEEE Transactions on Neural Networks, Vol.14, No.5, pp.1162-1175, September 2003. 

[22] Y. KANAZAWA and K. KANATANI, Image mosaicing by stratified matching, Image and Vision computing, Vol.22, pp.93-103, 2004. 

[23] Y. ZHOU, H. XUE and M. WAN, Inverse image alignment methode for image mosaicing and video stabilization in fundus indocyanine green angiography under confocal scanning laser ophthalmoscope, Computerized Medical Imaging and Graphics,Vol.27, pp.513-523, 2003. 

[24] P.F. MCLAUCHLAN and A. JAENICKE, Image mosaicing using sequential bundle adjustment, Image and Vision computing, Vol.20, pp.751-759, 2002. 

[25] A.K. JAIN and A. ROSS, Fingerprint Mosaicking, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Orlando, Florida, May, 2002. 

[26] D.N. WOOD, A. FINKELSTEIN, J.F. HUGHES, C.E. THAYER and D.H. SALESIN, Multiperspective Panoramas for Cel Animation, Proceedings of SIGGRAPH 97, pp.243-250, august, 1997. 

[27] P. RADEMACHER and G. BISHOP, Multiple-Center-of-Projection Images, Proceedings of SIGGRAPH, pp.199-206, 1998. 

[28] C. LANGIS, M. GREENSPAN and G. GODIN, The Parallel Iterative Closest Point Algorithm, Proceedings of the Third International Conference on 3D Digital Imaging and Modeling (3DIM), Québec, Canada, 2001. 

[29] D. VALENTIN, H. ABDI, A.J. O’TOOLE and G.W. COTTRELL, Connectionist models of face processing: A survey, Pattern Recognition, Vol.27, 1208-1230, 1994. 

[30] H. ABDI, A generalized approach for connectionist auto-associative memories: interpretation, implications and illustration for face processing. In J. Demongeot (Ed.), Artificial Intelligence and Cognitive Sciences. Manchester: Manchester University Press, (1988). 

[31] H. ABDI, D. VALENTIN and B. EDELMAN, Neural Networks, Sage, Thousand Oaks, 1999. 

[32] H. ABDI, D. VALENTIN and A. O’TOOLE, A generalized autoassociator model for face semantic process, in Optimization and neural network, edited by D. Levine (Erlbaum, Hillsdale), 1997. 

[33] A.J. O’TOOLE, F. JIANG, H. ABDI and J.V. HAXBY, Partially distributed representations of objects and faces in ventral temporal cortex, Journal of Cognitive Neuroscience, Vol.17, (in press, 2005).