Abstract
The dynamical organization or “binding” of elementary constituents into larger structures forms an essential operation for most information processing systems. Synchronization of temporal oscillations has been proposed as a major mechanism to achieve such organization in neural networks. We present an alternative approach, based on the competitive dynamics of tonic neurons in a layered network architecture. We discuss some properties of the resulting “Competitive Layer Model (CLM)” system and show that the proposed dynamics can give rise to Gestalt-like grouping operations for visual patterns and can model some characteristics of human visual perception. Finally, we report on an approach how the necessary, task-dependent interactions can be formed by learning from labeled grouping examples and sketch as an application of the system segmentation of biomedical images.
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
Brodatz P (1966) Texture:A Photographic Album for Artists and Designers. Dover, NewYork.
Daugman JG (1985) Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. J Opt Soc Am A 2(7):1160–1169.
Dunn D, Higgins WE, Wakeley J (1994) Texture segmentation using 2D Gabor elementary functions. IEEE Trans Pattern Anal Machine Intell 16(2):130–149.
Eckhorn R (1999) Neural mechanisms of visual feature binding investigated with microelectrodes and models. Vis Cogn 6:231–265.
Feng J (1997) Lyapunov functions for neural nets with nondifferentiable inputoutput characteristics. Neural Comput 9:43–49.
Hahnloser RHR, Sarpeshkar R, Mahowald MA, Douglas RJ, Seung HS (2000) Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit. Nature 405:947–951.
Hinton GE (1990) Mapping part-whole hierarchies into connectionist networks. Artific Intell 46 47–75.
Jones J, Palmer L (1987) An evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex. J Neurophysiol 58:1233–1258.
Julesz B (1981) Textons, the elements of texture perception and their interaction. Nature 290:91–97.
Köhler W (1929) Gestalt Psychology. Liveright, New York.
Kröse BJ (1987) Local structure analyzers as determinants of preattentive pattern discrimination. Biol Cybernet 55:289–298.
Lowe DG (1985) Perceptual Organization and Visual Recognition, Kluwer Academic Publishers, Boston.
Von der Malsburg C (1981) The Correlation Theory of Brain Function. Internal report 81–2, Max Planck Institute for Biophysical Chemistry, Göttingen, Germany.
Ma WY, Manjunath BS (1996) Texture features and learning similarity. In Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition.
Manjunath BS, Ma WY (1996) Texture features for browsing and retrieval of image data. IEEE Trans Pattern Anal Machine Intell 18(8):837–842.
Nattkemper TW, Wersing H, Schubert W, Ritter H (2000) Fluorescence micrograph segmentation by gestalt-based feature binding. In Proceedings of the International Joint Conference on Neural Networks (IJCNN), 248–254.
Nattkemper TW, Ritter H, Schubert W (2001) A neural classificator enabling high-throughput topological analysis of lymphocytes in tissue sections. IEEE Trans Inf Techn in Biomed 5 (2):138–149.
Ontrup J, Wersing H, Ritter H (2004) A computational feature binding model of human texture perception. Cogn Process 5 (1):32–44.
Ritter H (1990) A spatial approach to feature linking. In Proceedings of the International Neural Network Conference, vol 2, 898–901, Paris.
Roskies AL (1999) The binding problem. Neuron 24:7–9.
Schillen TB, König P (1994) Binding by temporal structure in multiple feature domains of an oscillatory network. Biol Cybernet 70:397–405.
Shadlen MN, Movshon JA (1999) Synchrony unbound:a critical evaluation of the temporal binding hypothesis. Neuron 24:67–77.
Singer W (1999) Neuronal synchrony:a versatile code for the definition of relations? Neuron, 24:49–65.
Terman D, Wang DL (1995) Global competition and local cooperation in a network of neural oscillators. Physica D 81:148–176.
von der Malsburg C, Buhmann J (1992) Sensory segmentation with coupled oscillators. Biol Cybernet 54:29–40.
Watson AB (1987) Efficiency of a model human image code. J Optical Soc Am A 4(12):2401–2417.
Weng S, Wersing H, Steil JJ, Ritter H (2006) Lateral interactions for feature binding and sensory segmentation from prototypic basis interactions. IEEE Trans Neural Networks 17 (3):(to appear).
Wersing H (2000) Spatial Feature Binding and Learning in Competitive Neural Layer Architectures. Cuvillier, Goettingen.
Wersing H, Steil JJ, Ritter H (2001) A competitive layer model for feature binding and sensory segmentation. Neural Comput 13(2):357–387.
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2007 Springer
About this chapter
Cite this chapter
Ritter, H., Weng, S., Ontrup, J., Steil, J. (2007). Gestalt Formation in a Competitive Layered Neural Architecture. In: Feng, J., Jost, J., Qian, M. (eds) Networks: From Biology to Theory. Springer, London. https://doi.org/10.1007/978-1-84628-780-0_8
Download citation
DOI: https://doi.org/10.1007/978-1-84628-780-0_8
Publisher Name: Springer, London
Print ISBN: 978-1-84628-485-4
Online ISBN: 978-1-84628-780-0
eBook Packages: Computer ScienceComputer Science (R0)