Abstract
Recognizing individuals of interest from faces captured with video cameras raises several challenges linked to changes in capture conditions (e.g., variation in illumination and pose). Moreover, in person re-identification applications, the facial models needed for matching are typically designed a priori, with a limited amount of reference samples captured under constrained temporal and spatial conditions. Tracking can, however, be used to regroup the system responses linked to a facial trajectory (facial captures from a person) for robust spatio-temporal recognition, and to update facial models over time using operational data. In this paper, an adaptive ensemble-based system is proposed for spatio-temporal face recognition (FR). Given a diverse set of facial captures in a trajectory of a target individual, an ensemble of 2-class classifiers is designed. A pool of ARTMAP classifiers is generated using a dynamic PSO-based learning strategy, and classifiers are selected and combined using Boolean combination. To train classifiers, target samples are combined with a set of reference non-target samples selected from the cohort and universal models using One-Sided Selection. During operations, facial trajectories are captured, and each individual-specific ensemble of the system seeks to detect target individuals, and possibly self-update their facial models. To update an ensemble, a learn-and-combine strategy is employed to avoid knowledge corruption, and a memory management strategy based on Kullback–Leibler divergence allows to rank and select stored validation samples over time to bound the system’s memory consumption. Spatio-temporal fusion is performed by accumulating classifier predictions over a time window, and a second threshold allows to self-update facial models. The proposed systems were validated with videos from the Face in Action and COX-S2V datasets, that feature both abrupt and gradual patterns of change. At the transaction level, results show that the proposed system allows to increase AUC accuracy by about 3 % for scenarios with abrupt changes, and by about 5 % with gradual changes. Subject-based analysis reveals the difficulties of face recognition with different poses, affecting more significantly the lamb- and goat-like individuals. Compared to reference spatio-temporal fusion approaches, results show that the proposed accumulation scheme produces the highest discrimination.
Similar content being viewed by others
Notes
A facial trajectory is defined as a set of facial captures (produced by face segmentation) that correspond to a same high-quality track of an individual across consecutive frames.
For simplicity of notation, the k has been omitted from all design data blocks, e.g., \(D_k^t \equiv D^t\).
References
Barry, M., Granger, E.: Face recognition in video using a what-and-where fusion neural network. In: IEEE International Conference on Neural Networks - Conference Proceedings, pp. 2256–2261. Orlando, United states (2007)
Best-Rowden, L., Klare, B., Klontz, J., Jain, A.: Video-to-video face matching: Establishing a baseline for unconstrained face recognition. In: Biometrics: Theory, Applications and Systems (BTAS), 2013 IEEE Sixth International Conference on, pp. 1–8 (2013)
Burghouts, G., Schutte, K., Bouma, H., Hollander, R.: Selection of negative samples and two-stage combination of multiple features for action detection in thousands of videos. Mach. Vision Appl. 25(1), 85–98 (2014). doi:10.1007/s00138-013-0514-0
Chen, L.F., Liao, H.Y., Lin, J.C.: Person identification using facial motion. In: Image Processing. Proceedings. 2001 International Conference on, vol. 2, pp. 677–680 (2001)
Chen, Y.C., Patel, V.M., Phillips, P.J., Chellappa, R.: Dictionary-based face and person recognition from unconstrained video. IEEE Trans. Image Process, 1–14 (2014) (preprint)
Cohen, I., Cozman, F.G., Sebe, N., Cirelo, M.C., Huang, T.S.: Semisupervised learning of classifiers: Theory, algorithms, and their application to human–computer interaction. IEEE Trans. Pattern Anal. Mach. Intell. 26(12), 1553–1567 (2004)
Connolly, J.F., Granger, E., Sabourin, R.: Evolution of heterogeneous ensembles through dynamic particle swarm optimization for video-based face recognition. Pattern Recognit. 45(7), 2460–2477 (2012)
DelaTorre, M., Granger, E., Radtke, P.V.W., Sabourin, R., Gorodnichy, D.O.: Incremental update of biometric models in face-based video surveillance. In: Proc. IJCNN, pp. 1–8. Brisbane, Australia (2012)
DelaTorre, M., Granger, E., Radtke, P.V.W., Sabourin, R., Gorodnichy, D.O.: Partially-supervised learning from facial trajectories for face recognition in video surveillance. Inf. Fusion 24, 31–53 (2015). doi:10.1016/j.inffus.2014.05.006
DelaTorre, M., Granger, E., Sabourin, R., Gorodnichy, D.O.: An individual-specific strategy for management of reference data in adaptive ensembles for face re-identification. In: IET (ed.) 5THh I. C. on Imaging for Crime Detection and Prevention (ICDP), pp. 1–7. London (2013)
DelaTorre, M., Radtke, P.V.W., Granger, E., Sabourin, R., Gorodnichy, D.O.: A comparison of adaptive matchers for screening of faces in video surveillance. In: Symposium on Computational Intelligence for Security and Defence Applications, pp. 1–8. Ottawa, Canada (2012)
Despiegel, V., Gentric, S., Fondeur, J.: Border control: From technical to operational evaluation. In: International Biometric Performance Testing Conference. Gaithersburg (2012)
Dewan, M., Granger, E., Roli, F., Sabourin, R., Marciallis, G.: A comparison of adaptive appearance methods for tracking faces in video surveillance. In: International Conference on Imaging for Crime Detection and Prevention (ICDP), pp. 1–8. London (2013)
Didaci, L., Roli, F.: Using co-training and self-training in semi-supervised multiple classifier systems. In: LNCS (including LNAI and LNB), LNCS, vol. 4109, pp. 522–530. Hong Kong (2006)
Doddington, G., Liggett, W., Martin, A., Przybocki, M., Reynolds, D.: Sheep, goats, lambs and wolves: A statistical analysis of speaker performance. In: International conference on spoken language processing, pp. 1351–1354 (1998)
Ekenel, H.K., Stallkamp, J., Stiefelhagen, R.: A video-based door monitoring system using local appearance-based face models. Comput. Vision Image Underst. 114(5), 596–608 (2010)
El Gayar, N., Shaban, S.A., Hamdy, S.: Face recognition with semi-supervised learning and multiple classifiers. In: Proc. of WSEAS Int. Conf. on Computational Intelligence, Man-Machine Systems and Cybernetics, pp. 296–301. USA (2006)
Fawcett, T.: An introduction to roc analysis. Pattern Recogn. Lett. 27(8), 861–874 (2006)
Fischer, M., Ekenel, H., Stiefelhagen, R.: Person re-identification in tv series using robust face recognition and user feedback. Multimed. Tools Appl. 55(1), 83–104 (2011)
Franco, A., Maio, D., Maltoni, D.: Incremental template updating for face recognition in home environments. Pattern Recogn. 43(8), 903–2891 (2010)
Goh, R., Liu, L., Liu, X., Chen, T.: The CMU Face In Action Database. In: Analysis and Modelling of Faces and Gestures, pp. 255–263. Carnegie Mellon University (2005)
Gorodnichy, D.: Video-based framework for face recognition in video. In: Proceedings. The 2nd Canadian Conference on Computer and Robot Vision, pp. 330–8. Piscataway (2005)
Hewitt, R., Belongie, S.: Active learning in face recognition: Using tracking to build a face model. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, p. 157. New York (2006)
Huang, Z., Shan, S., Wang, R., Zhang, H., Lao, S., Kuerban, A., Chen, X.: A benchmark and comparative study of video-based face recognition on cox face database. Accepted for publication, IEEE Transactions on Image Processing (2015)
Jain, A.K., Ross, A.: Learning user-specific parameters in a multibiometric system. In: Int. Conf. on Image Processing, pp. 57–60 (2002)
Kamgar-Parsi, B., Lawson, W., Kamgar-Parsi, B.: Toward development of a face recognition system for watchlist surveillance. IEEE Trans. PAMI 33(10), 1925–1937 (2011)
Khreich, W., Granger, E., Miri, A., Sabourin, R.: A comparison of techniques for on-line incremental learning of hmm parameters in anomaly detection. In: Proceedings of the 2009 IEEE Symposium on Computational Intelligence in Security and Defense Applications, pp. 2732–2752 (2010)
Khreich, W., Granger, E., Miri, A., Sabourin, R.: Iterative Boolean Combination of classifiers in the ROC space: An application to anomaly detection with HMMs. Pattern Recogn. 43(8), 2732–2752 (2010)
Klare, B., Jain, A.: On a taxonomy of facial features. In: International Conference on Biometrics: Theory Applications and Systems (BTAS), pp. 1–8 (2010)
Kubat, M., Matwin, S.: Addressing the curse of imbalanced training sets: One-sided selection. In: Proceedings of the Fourteenth International Conference on Machine Learning, pp. 179–186. Morgan Kaufmann (1997)
Kuncheva, L.: Combining Pattern Classifiers: Methods and Algorithms. Wiley (2004)
Lee, K.C., Ho, J., Yang, M.H., Kriegman, D.: Video-based face recognition using probabilistic appearance manifolds. In: Proc. in CVPR, vol. 1, pp. I–313, I–320 (2003)
Lee, K.C., Ho, J., Yang, M.H., Kriegman, D.: Visual tracking and recognition using probabilistic appearance manifolds. Comput. Vision Image Underst. 99, 303–331 (2005)
Li, F., Wechsler, H.: Open set face recognition using transduction. IEEE Trans. PAMI 27(11), 1686–1697 (2005)
Lim, C.P., Harrison, R.F.: Probabilistic fuzzy artmap: An autonomous neural network architecture for bayesian probability estimation. In: Artificial Neural Networks, Fourth Int. Conf. on, pp. 148–153 (1995)
Lim, C.P., Harrison, R.F.: An incremental adaptive network for on-line supervised learning and probability estimation. Neural Netw. 10(5), 925–939 (1997)
Liu, X., Cheng, T.: Video-based face recognition using adaptive Hidden Markov Models. In: Proceedings 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 340–345. Los Alamitos (2003)
Lu, K., Ding, Z., Zhao, J., Wu, Y.: A novel semi-supervised face recognition for video. In: Proc. of the International Conference on Intelligent Control and Information Processing, pp. 313–316 (2010)
Lu, Z., Wu, X., Bongard, J.: Active learning with adaptive heterogeneous ensembles. In: Proceedings of the 2009 Ninth IEEE International Conference on Data Mining (ICDM 2009), pp. 327–36. Piscataway (2009)
Matta, F., Dugelay, J.L.: Video face recognition: A physiological and behavioural multimodal approach. In: Proceedings—International Conference on Image Processing, ICIP, vol. 4, pp. IV497–IV500. San Antonio (2006)
Matta, F., Dugelay, J.L.: Person recognition using facial video information: a state of the art. J. Visual Lang. Comput. 20(3), 180–187 (2009)
Ojala, T., Pietikainen, M., Maenpaa, T.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Tr. PAMI 24(7), 971–987 (2002)
Okada, K., Kite, L., von der Malsburg, C.: An adaptive person recognition system. In: Proceedings 10th IEEE International Workshop on Robot and Human Interactive Communication, pp. 436–41. Piscataway (2001)
Pagano, C., Granger, E., Sabourin, R., Gorodnichy, D.O.: Detector ensembles for face recognition in video surveillance. In: IJCNN, pp. 1–8. Brisbane (2012)
Polikar, R., Udpa, L., Udpa, S.S., Honavar, V.: Learn++: An Incremental Learning Algorithm for MLP Networks. IEEE Trans. SMC 31(4), 497–508 (2001)
Rattani, A.: Adaptive biometric system based on template update procedures. Ph.D. thesis, University of Cagliari (2010)
Rattani, A., Freni, B., Marcialis, G.L., Roli, F.: Template update methods in adaptive biometric systems: A critical review. In: Lecture Notes in Computer Science (included Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics), vol. 5558, pp. 847–856. Alghero (2009)
Rattani, A., Marcialis, G., Roli, F.: Capturing large intra-class variations of biometric data by template co-updating. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, pp. 1–6. Piscataway (2008)
Roli, F., Didaci, L., Marcialis, G.: Template co-update in multimodal biometric systems. In: International Conference on Biometrics, vol. 4642, pp. 1194–202. Seoul (2007)
Roli, F., Didaci, L., Marcialis, G.L.: Adaptive biometric systems that can improve with use. In: Govindaraju, N.R.V. (ed.) Advances in Biometrics: Sensors, Systems and Algorithms, pp. 447–471. Springer (2008)
Roli, F., Marcialis, G.L.: Semi-supervised pca-based face recognition using self-training. In: JIAPR - Int. Workshop on Structural and Syntactical Pat. Rec. and Statistical Techniques in Pat. Rec., vol. 4109, pp. 560–568. Springer, Hong Kong (2006)
Ross, D.A., Lim, J., Lin, R.S., Yang, M.H.: Incremental learning for robust visual tracking. Int. J. Comput. Vision (2008) (Special issue: Learning for vision)
Satta, R.: Appearance descriptors for person re-identification: A comprehensive review. arXiv:1307.5748v1 (2013)
Singh, R., Vatsa, M., Ross, A., Noore, A.: Biometric classifier update using online learning: A case study in near infrared face verification. Image Vision Comput. 28, 1098–1105 (2010)
Tax, D., Duin, R.: Growing a multi-class classifier with a reject option. Pattern Recogn. 29(10), 1565–1570 (2008)
Turk, M., Pentland, A.: Eigenfaces for recognition. J. Cogn. Neurosci. 3(1), 71–86 (1991)
Viola, P., Jones, M.: Robust real-time face detection. Int. J. Comput. Vision 2(57), 137–154 (2004)
Yilmaz, A., Javed, O., Shah, M.: Object tracking: A survey. ACM Comput. Surv. 38(4) (2006)
Yu, G., Zhang, G., Domeniconi, C., Yu, Z., YouZ, J.: Semi-supervised classification based on random subspace dimensionality reduction. Pattern Recogn. 45(3), 1119–1135 (2012)
Zenobi, G., Cunningham, P.: Using diversity in preparing ensembles of classifiers based on different feature subsets to minimize generalization error. In: Raedt, L., Flach, P. (eds.) Machine Learning: ECML 2001. Lecture Notes in Computer Science, vol. 2167, pp. 576–587. Springer, Berlin, Heidelberg (2001)
Zhang, Y., Martnez, A.M.: A weighted probabilistic approach to face recognition from multiple images and video sequences. Image Vision Comput. 24, 626–638 (2006)
Zhou, S., Chellappa, R., Moghaddam, B.: Visual tracking and recognition using appearance-adaptive models in particle filters. Image Process. IEEE Trans. 13(11), 1491–1506 (2004)
Acknowledgments
This work was partially supported by the Natural Sciences and Engineering Research Council of Canada, and the Defence Research and Development Canada’s Centre for Security Science Public Security Technical Program (project PSTP-03-401BIOM). This work was also supported by the Program for the Improvement of the Professoriate of the Secretariat of Public Education, Mexico, the Mexican National Council for Science and Technology, and the University Center of Los Valles, University of Guadalajara, Ameca, Mexico.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
De-la-Torre, M., Granger, E., Sabourin, R. et al. An adaptive ensemble-based system for face recognition in person re-identification. Machine Vision and Applications 26, 741–773 (2015). https://doi.org/10.1007/s00138-015-0697-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00138-015-0697-7