Abstract
This paper addresses the problem of encoding and classifying spatio-temporal patterns, which are typical for human actions or gestures. The proposed method has the following main contributions: (i) it requires a very small number of training examples, (ii) it accepts variable sized input patterns, (iii) it is invariant to scale and translation, and (iv) it enables early recognition, from only partial information of the pattern. The underlying representation employed is a spiking neural network with axonal conductance delay. We designed a novel approach for mapping spatio-temporal patterns to spike trains, which are used to stimulate the network. The pattern features emerge in the network as a result of this stimulation in the form of polychronous neuronal groups, which are used for classification. The proposed method is validated on a set of gestures representing the digits from \(0\) to \(9\), extracted from video data of a human drawing the corresponding digits. The paper presents a comparison with several other standard pattern recognition approaches. The results show that the proposed approach significantly outperforms these methods, it is invariant to scale and translation, and it has the ability to recognize patterns from only partial information.
Similar content being viewed by others
References
Arulampalam MS, Maskell S, Gordon N, Clapp T (2002) A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking. IEEE Trans Signal Process 50(2):174–188
Bahlmann C, Burkhardt H (2004) The writer independent online handwriting recognition system frog on hand and cluster generative statistical dynamic time warping. IEEE Trans Pattern Anal Mach Intel 26(3):299–310
Beyeler M, Dutt ND, Krichmar JL (2013) Categorization and decision-making in a neurobiologically plausible spiking network using a stdp-like learning rule. Neural Netw 48:109–124
Bobick AF, Wilson AD (1997) A state-based approach to the representation and recognition of gesture. IEEE Trans Pattern Anal Mach Intel 19(12):1325–1337
Carreira-Perpinan MA, Hinton GE (2005) On contrastive divergence learning. In: Proceedings of the tenth international workshop on artificial intelligence and statistics, Citeseer, pp 33–40
Chang C-C, Lin C-J (2011) Libsvm: a library for support vector machines. ACM Trans Intel Syst Technol 2(3):27
Ciresan DC, Meier U, Gambardella LM, Schmidhuber J (2010) Deep, big, simple neural nets for handwritten digit recognition. Neural Comput 22(12):3207–3220
Davis J, Shah M (1994) Visual gesture recognition. In: IEEE proceedings of vision, image and signal processing, IET, vol 141, pp 101–106
Djioua M, Plamondon R (2009) A new algorithm and system for the characterization of handwriting strokes with delta-lognormal parameters. IEEE Trans Pattern Anal Mach Intel 31(11):2060–2072
Doucet A, De Freitas N, Gordon N (2001) Sequential Monte Carlo methods in practice. Springer, New York
Duda PE, Richard O (1973) Hart, pattern classification and scene analysis. Wiley-Interscience, Oxford
Gonzalez RC, Woods RE (2002) Digital image processing. Gatesmark Publishing, Knoxville
Graves A, Liwicki M, Fernández S, Bertolami R, Bunke H, Schmidhuber J (2009) A novel connectionist system for unconstrained handwriting recognition. IEEE Trans Pattern Anal Mach Intel 31(5):855–868
Haykin S, Network N (2004) A comprehensive foundation. Neural Netw 2:2004
Hinton G, Osindero S, Teh Y-W (2006) A fast learning algorithm for deep belief nets. Neural Comput 18(7):1527–1554
Hong P, Turk M, Huang TS (2000) Gesture modeling and recognition using finite state machines. In: Proceedings of fourth IEEE international conference on automatic face and gesture recognition, pp 410–415
Hu J, Gek Lim S, Brown MK (2000) Writer independent on-line handwriting recognition using an HMM approach. Pattern Recog 33(1):133–147
Isard M, Blake A (1996) Contour tracking by stochastic propagation of conditional density. In: Computer visionECCV’96. Springer, New York, pp 343–356
Isard M, Blake A (1998) Condensationconditional density propagation for visual tracking. Int J Comput Vis 29(1):5–28
Izhikevich EM (2006) Polychronization: computation with spikes. Neural Comput 18(2):245–282
Izhikevich EM et al (2003) Simple model of spiking neurons. IEEE Trans Neural Netw 14(6):1569–1572
Izhikevich EM, Gally JA, Edelman GM (2004) Spike-timing dynamics of neuronal groups. Cereb Cortex 14(8):933–944
Jaccard P (1912) The distribution of the flora in the alpine zone. 1. New Phytol 11(2):37–50
Kandel ER, Schwartz JH, Jessell TM et al (2000) Principles of neural science, vol 4. McGraw-Hill, New York
Karimpouli S, Fathianpour N, Roohi J (2010) A new approach to improve neural networks’ algorithm in permeability prediction of petroleum reservoirs using supervised committee machine neural network (scmnn). J Pet Sci Eng 73(3):227–232
Kass M, Witkin A, Terzopoulos D (1988) Snakes: active contour models. Int J Comput Vis 1(4):321–331
Kwok C, Fox D, Meila M (2004) Real-time particle filters. Proc IEEE 92(3):469–484
LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324
Liwicki M, Bunke H, et al. (2006) Hmm-based on-line recognition of handwritten whiteboard notes. In: Tenth international workshop on frontiers in handwriting recognition
Marquardt DW (1963) An algorithm for least-squares estimation of nonlinear parameters. J Soc Ind Appl Math 11(2):431–441
Murphy KP (2012) Machine learning: a probabilistic perspective. MIT Press, Cambridge
Palm RB (2012) Prediction as a candidate for learning deep hierarchical models of data. Technical University of Denmark, Palm
Paugam-Moisy H, Martinez R, Bengio S (2008) Delay learning and polychronization for reservoir computing. Neurocomputing 71(7):1143–1158
Rabiner L (1989) A tutorial on hidden markov models and selected applications in speech recognition. Proc IEEE 77(2):257–286
Ramamoorthy A, Vaswani N, Chaudhury S, Banerjee S (2003) Recognition of dynamic hand gestures. Pattern Recog 36(9):2069–2081
Rekabdar B, Joorabian M, Shadgar B (2012) Artificial neural network ensemble approach for creating a negotiation model with ethical artificial agents. In: Artificial intelligence and soft computing. Springer, New York, pp 493–501
Rekabdar B, Nicolescu M, Kelley R, Nicolescu M (2014) Unsupervised learning of spatio-temporal patterns using spike timing dependent plasticity. In: Artificial general intelligence. Springer, New York, pp 254–257
Rekabdar B, Nicolescu M, Kelley R, Nicolescu M (2015) An unsupervised approach to learning and early detection of spatio-temporal patterns using spiking neural networks. J Intel Robot Syst 77(1):1–15. doi:10.1007/s10846-015-0179-1
Samaria F, Young S (1994) Hmm-based architecture for face identification. Image Vis Comput 12(8):537–543
Tao X, Michel HE (2004) Data clustering via spiking neural networks through spike timing-dependent plasticity. In: IC-AI, pp 168–173
Welch G, Bishop G (1995) An introduction to the Kalman filter. Technical Report TR 95-041, Department of Computer Science, University of North Carolina
Yamato J, Ohya J, Ishii K (1992) Recognizing human action in time-sequential images using hidden markov model. In: Proceedings of IEEE computer society conference on computer vision and pattern recognition CVPR’92, pp 379–385
Yang M-H, Ahuja N (2001) Recognizing hand gestures using motion trajectories. In: Face detection and gesture recognition for human–computer interaction. Springer, New York, pp 53–81
Yeasin M, Chaudhuri S (2000) Visual understanding of dynamic hand gestures. Pattern Recog 33(11):1805–1817
Acknowledgments
We would like to thank the anonymous reviewers for their useful comments on improving our manuscript. This work has been supported by ONR Grant #N000141210860.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Rekabdar, B., Nicolescu, M., Nicolescu, M. et al. A Scale and Translation Invariant Approach for Early Classification of Spatio-Temporal Patterns Using Spiking Neural Networks. Neural Process Lett 43, 327–343 (2016). https://doi.org/10.1007/s11063-015-9436-3
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-015-9436-3