Image segmentation by a network of oscillators with memory

The authors propose a model of coupled phase oscillators with noise that performs segmentation of objects using a set of stored images each consisting of figures and a background. The amplitudes of the oscillators encode the spatial distribution and distribution of features of the external stimulus. In the learning stage the couplings between the phases are modified in a Hebb-like manner. It is shown that an external stimulus whose local features resemble those of one or several of the stored figures causes a selective phase coherence that retrieves the stored pattern of segmentation