Abstract
Efficient and accurate representation of a collection of images, that belong to the same class, is a major research challenge for practical image set classification. Existing methods either make prior assumptions about the data structure, or perform heavy computations to learn structure from the data itself. In this paper, we propose an efficient image set representation that does not make any prior assumptions about the structure of the underlying data. We learn the nonlinear structure of image sets with deep extreme learning machines that are very efficient and generalize well even on a limited number of training samples. Extensive experiments on a broad range of public datasets for image set classification show that the proposed algorithm consistently outperforms state-of-the-art image set classification methods both in terms of speed and accuracy.
Similar content being viewed by others
References
Bengio Y (2009) Learning deep architectures for AI. Found Trends Mach Learn 2(1):1–127
Bengio Y, Courville A, Vincent P (2013) Representation learning: a review and new perspectives. IEEE Trans PAMI 35(8):1798–1828
Cevikalp H, Triggs B (2010) Face recognition based on image sets. In: CVPR, pp 2567–2573
Chen S, Sanderson C, Harandi MT, Lovell BC (2013) Improved image set classification via joint sparse approximated nearest subspaces. In: CVPR, pp. 452–459
Cui Z, Chang H, Shan S, Ma B, Chen X (2014) Joint sparse representation for video-based face recognition. Neurocomputing 135:306–312
Du JX, Shao MW, Zhai CM, Wang J, Tang Y, Chen CLP (2015) Recognition of leaf image set based on manifoldmanifold distance. Neurocomputing 188:131–138
Gross R, Shi J (2001) The cmu motion of body database. Tech. Rep. CMU-RI-TR-01-18, Robotics Institute
Han B, He B, Sun T, Yan T, Ma M, Shen Y, Lendasse A (2016) HSR: \(l_{1/2}\)-regularized sparse representation for fast face recognition using hierarchical feature selection. Neural Comput Appl 27(2):305–320
Harandi M, Salzmannl M, Baktashmotlagh M (2015) Beyond gauss: image-set matching on the riemannian manifold of pdfs. In: ICCV
Harandi M, Sanderson C, Shirazi S, Lovell B (2011) Graph-embedding discriminant analysis on grassmannian manifolds for improved image set matching. In: CVPR, pp 2705–2712
Harandi MT, Salzmann M, Hartley R (2014) From manifold to manifold: geometry-aware dimensionality reduction for SPD matrices. In: ECCV, pp 17–32
Hayat M, Bennamoun M, An S (2014) Learning nonlinear reconstruction models for image set classification. In: CVPR, pp 1915–1922
Hu Y, Mian A, Owens R (2012) Face recognition using sparse approximated nearest points between image sets. IEEE Trans PAMI 34(10):1992–2004
Huang G (2015) What are extreme learning machines? Filling the gap between Frank Rosenblatt’s dream and John von Neumann’s puzzle. Cognit Comput 7(3):263–278
Huang GB, Chen L, Siew CK (2006) Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Trans Neural Netw 17(4):879–892
Huang GB, Zhou H, Ding X, Zhang R (2012) Extreme learning machine for regression and multiclass classification. IEEE Trans SMC Part B 42(2):513–529
Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70(1–3):489–501
Huang Z, Wang R, Shan S, Chen X (2015) Projection metric learning on Grassmann manifold with application to video based face recognition. In: CVPR, pp 140–149
Huang Z, Wang R, Shan S, Li X, Chen X (2015) Log-euclidean metric learning on symmetric positive definite manifold with application to image set classification. In: ICML
Johnson W, Lindenstrauss J (1984) Extensions of Lipschitz mappings into a Hilbert space. Conference in modern analysis and probability 26:189–206
Kasun LLC, Zhou H, Huang GB (2013) Representational learning with ELMs for big data. IEEE Intell Syst 28(6):30–59
Kim TK, Kittler J, Cipolla R (2007) Discriminative learning and recognition of image set classes using canonical correlations. IEEE Trans PAMI 29(6):1005–1018
Kim M, Kumar S, Pavlovic V, Rowley H (2008) Face tracking and recognition with visual constraints in real-world videos. In: CVPR, pp 1–8
Lan Y, Hu Z, Soh YC, Huang GB (2013) An extreme learning machine approach for speaker recognition. Neural Comput Appl 22(3):417–425
Lee KC, Ho J, Yang MH, Kriegman D (2003) Video-based face recognition using probabilistic appearance manifolds. In: CVPR, pp I313–I320
Leibe B, Schiele B (2003) Analyzing appearance and contour based methods for object categorization. In: CVPR, pp 409–415
Li B, Li Y, Rong X (2013) The extreme learning machine learning algorithm with tunable activation function. Neural Comput Appl 22(3):531–539
Liu L, Zhang L, Liu H, Yan S (2014) Towards large-population face identification in unconstrained videos. IEEE Trans CSVT PP(99):1–1
Liu X, Lin S, Fang J, Xu Z (2015) Is extreme learning machine feasible? a theoretical assessment (part i). IEEE Trans Neural Netw Learn Syst 26(1):7–20
Lu J, Wang G, Deng W, Moulin P (2014) Simultaneous feature and dictionary learning for image set based face recognition. In: ECCV, pp 265–280
Lu J, Wang G, Deng W, Moulin P, Zhou J (2015) Multi-manifold deep metric learning for image set classification. In: CVPR, pp 1137–1145
Lu J, Wang G, Moulin P (2013) Image set classification using holistic multiple order statistics features and localized multi-kernel metric learning. In: ICCV, pp 329–336
Mahmood A, Mian A, Owens R (2014) Semi-supervised spectral clustering for image set classification. In: CVPR, pp 121–128
Mian A, Hu Y, Hartley R, Owens R (2013) Image set based face recognition using self-regularized non-negative coding and adaptive distance metric learning. IEEE Trans Image Process 22:5252–5262
Nian R, He B, Lendasse A (2013) 3D object recognition based on a geometrical topology model and extreme learning machine. Neural Comput Appl 22(3):427–433
Ross D, Lim J, Lin R, Yang M (2008) Incremental learning for robust visual tracking. Int J Comput Vis 77:125–141
Uzair M, Mahmood A, Mian A, McDonald C (2013) A compact discriminative representation for efficient image-set classification with application to biometric recognition. In: International conference on biometrics, pp 1–8
Uzair M, Mahmood A, Mian A, McDonald C (2014) Periocular region-based person identification in the visible, infrared and hyperspectral imagery. Neurocomputing 149(Part B):854–867
Viola P, Jones M (2004) Robust real-time face detection. Int J Comput Vis 57:137–154
Wang GG, Lu M, Dong YQ, Zhao XJ (2016) Self-adaptive extreme learning machine. Neural Comput Appl 27(2):291–303
Wang R, Chen X (2009) Manifold discriminant analysis. In: CVPR, pp 429–436
Wang R, Guo H, Davis L, Dai Q (2012) Covariance discriminative learning: a natural and efficient approach to image set classification. In: CVPR, pp 2496–2503
Wang R, Shan S, Chen X, Gao W (2008) Manifold-manifold distance with application to face recognition based on image set. In: CVPR, pp 1–8
Wang W, Wang R, Huang Z, Shan S, Chen X (2015) Discriminant analysis on Riemannian manifold of Gaussian distributions for face recognition with image sets. In: CVPR
Xie L, Lu C, Mei Y, Du H, Man Z (2016) An optimal method for data clustering. Neural Comput Appl 27(2):283–289
Zhu P, Zhang L, Zuo W, Zhang D (2013) From point to set: extend the learning of distance metrics. In: ICCV, pp 2664–2671
Acknowledgements
This work was supported by the Australian Research Council (ARC) Grant DP110102399 and UWA Research Collaboration Award 2014.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Uzair, M., Shafait, F., Ghanem, B. et al. Representation learning with deep extreme learning machines for efficient image set classification. Neural Comput & Applic 30, 1211–1223 (2018). https://doi.org/10.1007/s00521-016-2758-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-016-2758-x