Abstract
The binding of similar objects to a common group is an effortless task for humans.We know if things belong together or not by intuitively relying on a set of rules. In the area of visual perception, these rules can be described by the Laws of Gestalt. Although these laws are intuitive for humans to understand, a computational feasible formulation can be demanding.We present an improved approach to learn the computational formulations for these laws from labeled training data. The approach learns attraction and repelling interactions between features, which in turn can be used in artificial neural networks to decided whether input features belong to a common group or have to be separated. The technique is evaluated within different perceptual grouping scenarios and with two kinds of artificial neural networks.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Arenas, A., Diaz-Guilera, A., Pérez-Vicente, C.J.: Synchronization processes in complex networks. Physica D: Nonlinear Phenomena 224(1), 27–34 (2006)
Bassett, D.S., Porter, M.A., Wymbs, N.F., Grafton, S.T., Carlson, J.M., Mucha, P.J.: Robust detection of dynamic community structure in networks. Chaos: An Interdisciplinary Journal of Nonlinear Science 23(1), 013,142–013,142 (2013)
Breve, F.A., Zhao, L., Quiles, M.G., Macau, E.E.: Chaotic phase synchronization and desynchronization in an oscillator network for object selection. Neural Networks 22(5), 728–737 (2009)
Chang, D., Nesbitt, K.V., Wilkins, K.: The gestalt principles of similarity and proximity apply to both the haptic and visual grouping of elements. In: Proceedings of the Eight Australasian Conference on User Interface, vol. 64, pp. 79–86. Australian Computer Society, Inc. (2007)
De Valois, R.L., Yund, W.E., Hepler, N.: The orientation and direction selectivity of cells in macaque visual cortex. Vision Research 22(5), 531–544 (1982)
Gallace, A., Spence, C.: To what extent do gestalt grouping principles influence tactile perception? Psychological Bulletin 137(4), 538 (2011)
Gray, C.M., Singer, W.: Stimulus-specific neuronal oscillations in orientation columns of cat visual cortex. Proceedings of the National Academy of Sciences 86(5), 1698–1702 (1989)
Heidemann, G., Ritter, H.J.: Efficient vector quantization using the wta-rule with activity equalization. Neural Processing Letters 13(1), 17–30 (2001)
Kuramoto, Y.: Chemical oscillations, waves, and turbulence. Dover (2003)
Li, C., Li, Y.: Fast and robust image segmentation by small-world neural oscillator networks. Cognitive Neurodynamics 5(2), 209–220 (2011)
Meier, M., Haschke, R., Ritter, H.J.: Learning of lateral interactions for perceptual grouping employing information gain. In: Mladenov, V., Koprinkova-Hristova, P., Palm, G., Villa, A.E.P., Appollini, B., Kasabov, N. (eds.) ICANN 2013. LNCS, vol. 8131, pp. 178–185. Springer, Heidelberg (2013)
Meier, M., Haschke, R., Ritter, H.J.: Perceptual grouping through competition in coupled oscillator networks. In: ESANN (2013b)
Meier, M., Haschke, R., Ritter, H.J.: Perceptual grouping by entrainment in coupled kuramoto oscillator networks. Network: Computation in Neural Systems 25(1-2), 72–84 (2014), http://informahealthcare.com/doi/abs/10.3109/0954898X.2014.882524 , doi:10.3109/0954898X.2014.882524
Nomura, A., Ichikawa, M., Okada, K., Miike, H., Sakurai, T., Mizukami, Y.: Image edge detection with discretely spaced fitzhugh-nagumo type excitable elements. In: 2011 Joint 3rd Int’l Workshop on Nonlinear Dynamics and Synchronization (INDS) & 16th Int’l Symposium on Theoretical Electrical Engineering (ISTET), pp. 1–8. IEEE (2011)
Ontrup, J., Wersing, H., Ritter, H.: A computational feature binding model of human texture perception. Cognitive Processing 5(1), 31–44 (2004)
Rao, S., Han, S., Principe, J.: Information theoretic vector quantization with fixed point updates. In: International Joint Conference on Neural Networks, IJCNN 2007, pp. 1020–1024 (2007), doi:10.1109/IJCNN.2007.4371098
Rényi, A.: Some fundamental questions of information theory. Selected Papers of Alfred Renyi 2(174), 526–552 (1976)
Ritter, H.: A spatial approach to feature linking. In: INNC (1990)
Treisman, A., et al.: The binding problem. Current Opinion in Neurobiology 6(2), 171–178 (1996)
Wagemans, J., Elder, J., Kubovy, M., Palmer, S., Peterson, M., Singh, M., von der Heydt, R.: A century of gestalt psychology in visual perception: I. perceptual grouping and figure-ground organization. Psychological Bulletin 138(6) (2012)
Wang, D.: Modeling global synchrony in the visual cortex by locally coupled neural oscillators. In: Eeckman, F.H. (ed.) Computation in Neurons and Neural Systems, pp. 109–114. Springer (1994)
Wang, D., Terman, D.: Locally excitatory globally inhibitory oscillator networks. IEEE Transactions on Neural Networks 6(1), 283–286 (1995)
Weng, S., Wersing, H., Steil, J., Ritter, H.: Learning lateral interactions for feature binding and sensory segmentation from prototypic basis interactions. IEEE Transactions on Neural Networks 17(4), 843–862 (2006)
Wersing, H.: Learning lateral interactions for feature binding and sensory segmentation. In: NIPS, pp. 1009–1016 (2001)
Wersing, H., Steil, J., Ritter, H.: A competitive-layer model for feature binding and sensory segmentation. Neural Computation 13(2), 357–387 (2001)
Yu, G., Slotine, J.J.: Visual grouping by neural oscillator networks. IEEE Transactions on Neural Networks 20(12), 1871–1884 (2009)
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
Meier, M., Haschke, R., Ritter, H.J. (2015). Learning Gestalt Formations for Oscillator Networks. In: Koprinkova-Hristova, P., Mladenov, V., Kasabov, N. (eds) Artificial Neural Networks. Springer Series in Bio-/Neuroinformatics, vol 4. Springer, Cham. https://doi.org/10.1007/978-3-319-09903-3_7
Download citation
DOI: https://doi.org/10.1007/978-3-319-09903-3_7
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-09902-6
Online ISBN: 978-3-319-09903-3
eBook Packages: EngineeringEngineering (R0)