Image segmentation by complex-valued units

Authors:
Cornelius Weber;Stefan Wermter
Affiliations:
Hybrid Intelligent Systems, SCAT, University of Sunderland, UK;Hybrid Intelligent Systems, SCAT, University of Sunderland, UK
Venue:
ICANN'05 Proceedings of the 15th international conference on Artificial Neural Networks: biological Inspirations - Volume Part I
Year:
2005

Citing 5
Cited 0

Stability and intermittency in large-scale coupled oscillator models for perceptual segmentation

Journal of Mathematical Psychology
Position invariant recognition in the visual system with cluttered environments

Neural Networks
Self-Organization of Orientation Maps, Lateral Connections, and Dynamic Receptive Fields in the Primary Visual Cortex

ICANN '01 Proceedings of the International Conference on Artificial Neural Networks
Complex-Valued Neural Networks: Theories and Applications (Series on Innovative Intelligence, 5)

Complex-Valued Neural Networks: Theories and Applications (Series on Innovative Intelligence, 5)
Object localisation using laterally connected "What" and "Where" associator networks

ICANN/ICONIP'03 Proceedings of the 2003 joint international conference on Artificial neural networks and neural information processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Spike synchronisation and de-synchronisation are important for feature binding and separation at various levels in the visual system. We present a model of complex valued neuron activations which are synchronised using lateral couplings. The firing rates of the model neurons correspond to a complex number’s absolute value and obey conventional attractor network relaxation dynamics, while the firing phases correspond to a complex number’s angle and follow the dynamics of a logistic map. During relaxation, we show that features with strong couplings are grouped by firing in the same phase and are separated in phase from features that are coupled weakly or by negative weights. In an example, we apply the model to the level of a hidden representation of an image, thereby segmenting it on an abstract level. We imply that this process can facilitate unsupervised learning of objects in cluttered background.