A dynamically coupled chaotic oscillatory correlation network

In this paper, a network of dynamically coupled chaotic maps for scene segmentation is proposed. It is a two-dimensional array consisting of discrete chaotic elements. Time evolution of chaotic maps corresponding to an object in the given scene are synchronized and desynchronized with respect to time evolution of chaotic elements corresponding to different objects. As a continuous chaotic oscillatory correlation network, this model can escape from the synchrony-desynchrony dilemma and so has unbounded capacity of segmentation too. In the present model, coupling range of each active element dynamically increases according to predefined rules, until a saturated state is achieved, i.e., locally coupled chaotic maps corresponding to an object at the start are coupled globally at the end. Consequently, both of the advantages of global coupling and local coupling are incorporated in a unique scheme. Another significant result is that good performance and transparent dynamics of the model are obtained by utilizing only one-dimensional chaotic map instead of complex neurons as each element