Binding and segmentation of visual images by means of oscillatory neurons

A neural network based on Wilson-Cowan oscillators is used to perform object recognition in a two-dimensional visual scene. The temporal correlation among groups of oscillating neurons is used as the main criterion to solve the classic binding and segmentation problem. The network uses an original pattern of short-range lateral excitations among adjacent neurons to achieve the binding problem, and an external inhibitory global neuron to provide segmentation of multiple objects in the same visual scene. The latter may represent an "attention mechanism" from neurons at a higher hierarchical level. Simulations performed by using multiple idealized figures (up to 4-5) in the presence of noise suggest that the network can satisfactorily recognize objects in most cases. However, the threshold and time constant of the attention mechanism depend on the complexity (number of objects and level of noise) of the scene under examination. The present results may be useful to improve our understanding of how distributed activities are integrated in the neural system to form single object perceptions. In perspective, the proposed model may find in practical algorithms for object recognition.