Abstract
This paper studies the problem of automatic person enrollment based on face-gait fusion within a context of anonymous identification. Enrollment should determine whether an observed subject has been seen before or not. Traditionally, this process has been embedded into a major identification system and its potential has been undervalued. This work claims that enrollment can be considered as a task in itself, and that there are real applications that can benefit from exclusively managing it. To this end, it is shown that the enrollment error model is different from that of anonymous identification. Enrollment experiments, conducted over three types of random permutations of probe samples, showed the benefits of face-gait fusion over single biometrics.
This work has been supported by the grants P1-1B2012-22 and PREDOC/2012/05 from Universitat Jaume I, PROMETEOII/2014/062 from Generalitat Valenciana, and TIN2013-46522-P from the Spanish Ministerio de Economía y Competitividad.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Note that the converse holds when scores encode similarities (rather than distances).
- 2.
The reader will find more details on methods and datasets in next sections.
References
DeCann, B., Ross, A.: “Has this person been encountered before?”: Modeling an anonymous identification system. In: CVPRW, pp. 89–96 (2012)
Zheng, W.S., Gong, S., Xiang, T.: Person re-identification by probabilistic relative distance comparison. In: CVPR, pp. 649–656 (2011)
Roy, A., Sural, S., Mukherjee, J.: A hierarchical method combining gait and phase of motion with spatiotemporal model for person re-identification. Pattern Recogn. Lett. 33(14), 1891–1901 (2012)
Geng, X., Smith-Miles, K., Wang, L., Li, M., Wu, Q.: Context-aware fusion: a case of study on fusion of gait and face for human identification in video. Pattern Recogn. 43, 3660–3673 (2010)
Hossain, E., Chetty, G.: Person identity verification based on multimodal face-gait fusion. Int. J. Comput. Sci. Netw. Secur. 11(6), 77–86 (2011)
Almohammad, M.S., Salama, G.I., Mahmoud, T.A.: Face and gait fusion methods: a survey. Int. J. Comput. Sci. Telecommun. 4(4), 19–28 (2013)
Martín-Félez, R., Xiang, T.: Gait recognition by ranking. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part I. LNCS, vol. 7572, pp. 328–341. Springer, Heidelberg (2012)
Han, J., Bhanu, B.: Individual recognition using Gait Energy Image. PAMI 28(2), 316–322 (2006)
Belhumeur, P.N., Hespanha, J.P., Kriegman, D.J.: Eigenfaces vs. fisherfaces: recognition using class specific linear projection. PAMI 19(7), 711–720 (1997)
Yu, S., et al.: A framework for evaluating the effect of view angle, clothing and carrying condition on gait recognition. In: 18th ICPR, pp. 441–444 (2006)
Martin, A., et al.: The DET curve in assessment of detection task performance. In: EuroSpeech, pp. 1895–1898 (1997)
Fawcett, T.: An introduction to ROC analysis. Pattern Recogn. Lett. 27(8), 861–874 (2006)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Ortells, J., Mollineda, R.A. (2015). Person Enrollment by Face-Gait Fusion. In: Paredes, R., Cardoso, J., Pardo, X. (eds) Pattern Recognition and Image Analysis. IbPRIA 2015. Lecture Notes in Computer Science(), vol 9117. Springer, Cham. https://doi.org/10.1007/978-3-319-19390-8_54
Download citation
DOI: https://doi.org/10.1007/978-3-319-19390-8_54
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-19389-2
Online ISBN: 978-3-319-19390-8
eBook Packages: Computer ScienceComputer Science (R0)