Convolutional Spiking Neural Network for Robust Object Detection with Population Code Using Structured Pulse Packets
Chapter
Abstract
We propose a convolutional spiking neural network (CSNN) model with population coding for robust object (e.g., face) detection. Basic structure of the network involves hierarchically alternating layers for feature detection and feature pooling. The proposed model implements hierarchical template matching by temporal integration of structured pulse packet. The packet signal represents some intermediate or complex visual feature (e.g., a pair of line segments, corners, eye, nose, etc.) that constitutes a face model. The output pulse of a feature pooling neuron represents some local feature (e.g., end-stop, blob, eye, etc.). Introducing a population coding scheme in the CSNN architecture, we show how the biologically inspired model attains invariance to changes in size and position of face and ensures the efficiency of face detection.
Keywords
convolutional neural networks object detection face detection population coding spiking neural networks pulse packetPreview
Unable to display preview. Download preview PDF.
References
- 1.Abeles M (1991) Corticonics: Neural circuits of the cerebral cortex. Cambridge: Cambridge University Press.CrossRefGoogle Scholar
- 2.Aviel Y, Mehring C, Abeles M, Horn, D (2003) On Embedding Synfire Chains in a Balanced Network. Neural Comput 15: 1321–1340MATHCrossRefGoogle Scholar
- 3.Baxter J (1997) A Bayesian/information theoretic model of learning to learn via multiple task sampling. Machine Learning, 28: 7–40 [2b]Google Scholar
- 4.Chen X, Gu L, Li S Z, Zhang H-J (2001) Learning Representative Local Features for Face Detection. Proc of Computer Vision and Pattern Recognition [2a]Google Scholar
- 5.Denev S, Lathan PE, Pouget A (1999) Reading population codes: a neural implementation of ideal observers. Nature Neuroscience 2: 740–745CrossRefGoogle Scholar
- 6.Diesmann M, Gewaltig MO, Aertsen A (1999) Stable propagation of synchronous spiking in cortical neural networks. Nature 402: 529–533CrossRefGoogle Scholar
- 7.Földiâk P (1991) Learning Invariance from Transformation Sequences. Neural Comput 3: 194–200CrossRefGoogle Scholar
- 8.Fujita I, Tanaka K, Ito M, Cheng K (1992) Columns for visual features of objects in monkey inferotemporal cortex. Nature 360: 343–346CrossRefGoogle Scholar
- 9.Fukushima K (1980) Neocognitron: A self-organizing Neural Network Model for a Mechanism of Pattern Recognition Unaffected by Shift in Position. Biol Cybern, 36: 193–202MathSciNetMATHCrossRefGoogle Scholar
- 10.Garg A, Agarwal S, Huang T S (2002) Fusion of Global and Local Information for Object Detection. Proc of the 16th Int Conf on Pattern Recog [6a]Google Scholar
- 11.Gu L, Li SZ, Zhang H (2001) Learning Probabilistic Distribution Model for Multi-View Face Detection. Proc of Computer Vision and Pattern Recognition.Google Scholar
- 12.Hasselmo M (2003) Theta theory: Requirements for encoding events and task rules explain theta phase relationships in hippocampus and neocortex. Proc of International Joint Conf On Neural NetworksGoogle Scholar
- 13.Hopfield J J (1995) Pattern recognition computation using action potential timing for stimulus representation. Nature, 376: 33–36CrossRefGoogle Scholar
- 14.Ikeda K (2003) A synfire chain in layered coincidence detectors in random synaptic delays. Neural Networks 16: 39–46CrossRefGoogle Scholar
- 15.Konen W K, von der Malsburg C (1993) Learning to generalize from single examples in the dynamic link architecture. Neural Comput 5: 1019–1030CrossRefGoogle Scholar
- 16.Korekado S, Morie T, Nomura O, Matsugu M, Iwata A (2003) A Convolutional Neural Network VLSI for Image Recognition Using Merged/Mixed Analog-Digital Architecture. Proc. of Seventh International Conference on Knowledge-Based Intelligent Information & Engineering System.Google Scholar
- 17.Krüger N (1998) Collinearity and Parallelism are Statistically Significant Second-Order Relations of Complex Cell Responses. Neural Processing Lett 8: 117–129CrossRefGoogle Scholar
- 18.Le Cun Y, Bengio T (1995) Convolutional networks for images, speech, and time series. In: Arbib MA (ed.) The Handbook of Brain Theory and Neural Networks. MIT Press, Boston, pp 255–258Google Scholar
- 19.Maass W (1999) Computing with Spiking Neurons. In: Maass W, Bishop C M (ed.) Pulsed Neural Networks. Cambridge: MIT Press, pp 55–85Google Scholar
- 20.Maass W, Natschlager T(1997) Networks of spiking neurons can emulate arbitrary Hopfield nets in temporal coding. Network: Computation in Neural Systems, 8: 355–372Google Scholar
- 21.Masuda N, Aihara K (2003) Duality of Rate Coding and Temporal Coding in Multilayered Feedforward Networks. Neural Comput 15: 103–125MATHCrossRefGoogle Scholar
- 22.Matsugu M (2001) Hierarchical Pulse-coupled Neural Network Model with Temporal Coding and Emergent Feature Binding Mechanism. Proc International Joint Conf On Neural Networks. pp 802–807Google Scholar
- 23.Matsugu M, Iijima K (2000; filed in 1994 ) Object Recognition Method. (in Japanese) Japanese Patent No P3078166Google Scholar
- 24.Matsugu M, Mori K, Ishii M, Mitarai Y (2002) Convolutional Spiking Neural Network Model for Robust Face Detection, Proc 9`h International Conf On Neural Info Processing. pp 660–664Google Scholar
- 25.Mitarai Y, Mori K, Matsugu M (2003) Robust Face Detection Systems Based on Conolutional Neural Networks Using Selective Activation of Modules. Proc 2“d Forum for Information Technology (in Japanese)Google Scholar
- 26.Mohan A, Papageorgiou C, Poggio T(2001) Example-Based Object Detection in Images by Components. IEEE Trans on Pattern Analysis and Machine Intelligence, 23: 349–361Google Scholar
- 27.Murase Y, Nayar S (1997) Detection of 3D objects in cluttered scenes using hierarchical eigenspace. Pattern Recog Lett 36: 375–384CrossRefGoogle Scholar
- 28.Natschlager T, Ruf B (1997) Learning radial basis functions with spiking neurons using action potential timing.Google Scholar
- 29.Riesenhuber M, Poggio T (1999) Hierarchical models of object recognition in cortex. Nature Neuroscience, 2: 1019–1025CrossRefGoogle Scholar
- 30.Rowley H, Baluja S, Kanade T (1998) Rotation Invariant Neural Network-Based Face Detection. Proc of Computer Vision and Pattern Recognition pp 38–44Google Scholar
- 31.Schneiderman H, Kanade T (2000) A Statistical Method for 3D Object Detection Applied to Faces and Cars. Proc of Computer Vision and Pattern RecognitionGoogle Scholar
- 32.Tanaka H, Hasegawa A, Mizuno H, Endo T (2002) Synchronizability of Distributed Clock Oscillators. IEEE Trans on Circuits and Sys I, 49: 1271–1278CrossRefGoogle Scholar
- 33.Tiesinga PHE, Sejnowski TJ (2001) Precision of pulse-coupled networks of integrateand-fire neurons. Network: Comput In Neural Sys 12: 215–233Google Scholar
- 34.Van Rullen R, Gautrais J, Delorme A, Thorpe S (1998) Face Processing Using One Spike per Neurone. BioSystems 48: 229–239CrossRefGoogle Scholar
- 35.Viola P, Jones M (2001) Rapid Object Detection using a Boosted Cascade of Simple Features. Proc Computer Vision and Pattern RecognitionGoogle Scholar
- 36.Weber M, Welling M, Perona P (2000) Unsupervised Learning of Models for Recognition. Proc European Conf Computer Vision, vol 1, pp 18–32Google Scholar
- 37.Wallis G, Rolls ET (1997) Invariant Face and Object Recognition in the Visual System. Prog in Neurobiol 51: 167–194CrossRefGoogle Scholar
- 38.Yang M-H, Kriegman D J, Ahuja N (2002) Detecting Faces in Images: A Survey. IEEE Trans on Pattern Analysis and Machine Intelligence, 24: 34–58Google Scholar
Copyright information
© Springer-Verlag Berlin Heidelberg 2004