Abstract
Although many algorithms have been proposed, face recognition and verification systems can guarantee a good level of performances only for controlled environments. In order to improve the performance and robustness of face recognition and verification systems, multi-modal and mono-modal systems based on the fusion of multiple recognisers using different or similar biometrics have been proposed, especially for verification purposes. In this paper, a recognition and verification system based on the combination of two well-known appearance-based representations of the face, namely, principal component analysis (PCA) and linear discriminant analysis (LDA), is proposed. Both PCA and LDA are used as feature extractors from frontal view images. The benefits of such a fusion are shown for different environmental conditions, namely, ideal conditions, characterised by a very limited variability of environmental parameters, and real conditions with a large variability of lighting, scale and facial expression.
Similar content being viewed by others
References
Jain AK, Bolle R, Pankanti S (eds) (1999) Biometrics: Personal identification in networked society. Kluwer Academic Publishers, Boston/Dordrecht/London
Wechsler H, Phillips JP, Bruce V, Folgeman Soulie F, Huang TS (eds) (1997) Face recognition – From theory to applications. ASI NATO series, vol 163, Springer, Berlin Heidelberg New York
Yang MH, Kriegman D, Ahuja N (2002) Detecting face images: A survey. IEEE T Pattern Anal 24(1):24–58
Ross A, Jain AK (2003) Information fusion in biometrics. Pattern Recogn Lett 24(13):2115–2125
Verlinde P, Druyts P, Chollet G, Acheroy M (1999) A multi-level data fusion approach for gradually upgrading the performances of identity verification systems. In: Dasarathy B (ed) Sensor fusion: Architectures, algorithms and application III, vol 3719. SPIE Press, Orlando, Florida, USA, pp 14–25
Achermann B, Bunke H (1996) Combination of classifiers on the decision level for face recognition. Technical report IAM-96–002, Institut für Informatik und angewandte Mathematik, Universität Bern, January 1996
Zhao WY, Chellappa R, Rosenfeld A, Philips PJ (2000) Face recognition: A literature survey. UMD CfAR technical report CAR-TR-948
Turk M, Pentland A (1991) Eigenfaces for face recognition. J Cognitive Neurosci 3(1):71–86
Belhumeur PN, Hespanha JP, Kriegman DJ (1997) Eigenfaces vs. fisherfaces: Recognition using class specific linear projection. IEEE T Pattern Anal 19(7):711–720
Wiskott L, Fellous JM, Krüger N, von der Malsburg C (1997) Face recognition by elastic bunch graph matching. IEEE T Pattern Anal 19(7):775–779
Kotropoulos CL, Tefas A, Pitas I (2000) Morphological elastic graph matching applied to frontal face authentication under well-controlled and real conditions. Pattern Recogn 33(12):1935–1947
Penev PS, Atick J (1996) Local feature analysis: A general statistical theory for object representation. Network–Comp Neural 7(3):477–500
de Vel O, Aeberhard S (1999) Line-based face recognition under varying pose. IEEE T Pattern Anal 21(10):1081–1088
Roli F, Kittler J (eds) (2002) Multiple classifier systems, Springer, Berlin Heidelberg New York LNCS 2364
Yu K, Yang XJ, Bunke H (1995) Face recognition by facial profile analysis. In: Bichsel M (ed) Proceedings of the international workshop on automatic face and gesture recognition, Zurich, Switzerland, June 1995, pp 208–213
Lucas SM (1997) The continuous n-tuple classifier and its application to face recognition. Electron Lett 33:1676–1678
Lin S, Kung S, Lin L (1997) Face recognition/detection by a probabilistic decision-based neural network. IEEE T Neural Networ 8(1):114–132
Lawrence S, Giles C, Tsoi A, Back A (1997) Face recognition: a convolutional neural network approach. IEEE T Neural Networ 8(1):98–113
Tolba AS, Abu-Rezq AN (2000) Combined classifier for invariant face recognition. Pattern Anal Appl 3(4):289–302
Roli F, Fumera G, Kittler J (2002) Fixed and trained combiners for fusion of unbalanced pattern classifiers. In: Proceedings of the 5th international conference on information fusion (IF 2002), Annapolis, Maryland (USA), 7–11 July 2002, pp 278–284
Tan T, Yan H (1999) Face recognition by fractal transformation. In: Proceedings of the IEEE ICASSP, Turkey, May 1999, pp 3537–3540
Messer K, Matas J, Kittler J, Luettin J, Maitre G (1999) XM2VTSdb: The extended M2VTS database. In: Proceedings of the 2nd international conference on audio- and video-based biometric person authentication, Washington, DC, March 1999
Luettin J, Matre G (1998) Evaluation protocol for the extended m2vts database (xm2vtsdb). Technical report IDIAP-COM 98–05, Dalle Mole Institute for Perceptual Artificial Intelligence,http://www.idiap.ch, July 1998
Marcialis GL, Roli F (2003) Fusion of face recognition algorithms for video-based surveillance systems, in multisensor surveillance systems: The Fusion Perspective. In: Foresti GL, Regazzoni C, Varshney P (eds) (2003) Kluwer Academic Publishers, Boston/Dordrecht/London, pp 235–250
Marcialis GL, Roli F (2002) Fusion of LDA and PCA for face verification. In: Tistarelli M, Bigun J, Jain AK (eds) (2002) Proceedings of the workshop on biometric authentication, Copenhagen, Denmark, June 2002, Springer, Berlin Heidelberg New York, LNCS 2359, pp 30–37
Duda RO, Hart PE, Stork DG (2001) Pattern Classification, Wiley, USA
Zhao W, Krishnaswamy A, Chellappa R, Swets D, Weng J (1998) Discriminant analysis of principal components for face recognition. In: Wechsler H, Phillips PJ, Bruce V, Soulie FF, Huang TS (eds) Face recognition: From theory to applications. Springer, Berlin Heidelberg New York, pp 73–85
Chen LF, Liao HYM, Ko MT, Lin JC, Yu GJ (2000) A new LDA-based face recognition system which can solve the small sample size problem. Pattern Recogn 33:1713–1726
Goudail F, Lange E, Iwamoto T, Kyuma K, Otsu O (1996) Face recognition system using local autocorrelation and multiscale integration. IEEE T Pattern Anal 18(10):1024–1028
Fukunaga K (1990) Introduction of statistical pattern recognition, Academic Press, New York
Liu K, Cheng YQ, Yang JY, Liu X (1992) A generalised optimal set of discriminant vectors. Pattern Recogn 25(7):731–729
Yang J, Yang J (2003) Why can LDA be performed in PCA transformed space? Pattern Recogn 36(2):563–566
Kittler J, Li YP, Matas J (2000) On matching scores for LDA-based face verification. In: Mirmehdi M, Thomas B (eds) Proceedings of the British Machine Vision Conference 2000, Bristol, UK, September 2000, pp 42–51
Martinez AM, Kak AC (2001) PCA versus LDA. IEEE T Pattern Anal 23(2):228–233
Mansfield T, Wayman J (2002) Best practices in testing and reporting performance of biometric devices. For the Biometrics Working Group. Technical report issue 2 draft 9, Centre for Mathematics and Scientific Computing, National Physics Laboratory, Middlesex, UK, February 2002
Lu X, Wang Y, Jain AK (2003) Combining classifiers for face recognition, Proc. ISME, IEEE Int. Cont. on Multimedia & Expo, vol. III, pp. 13–16, Baltimore, MD, July 6–9, 2003
Acknowledgments
This work was partially supported by the Italian Ministry of University and Scientific Research (MIUR) in the framework of the research project on distributed systems for multisensor recognition with augmented perception for ambient security and customisation.
The authors also wish to thank the anonymous referees for the useful and constructive comments and suggestions, which allowed them to substantially improve the paper.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Marcialis, G.L., Roli, F. Fusion of appearance-based face recognition algorithms. Pattern Anal Applic 7, 151–163 (2004). https://doi.org/10.1007/s10044-004-0212-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-004-0212-7