Title :
Locally coupled chaotic oscillator network for scene segmentation
Author :
Liang, Zhao ; Omar, Nizam ; Macau, Elbert E N
Author_Institution :
Inst. Tecnologico de Aeronaut., Brazil
Abstract :
A chaotic oscillatory correlation network for scene segmentation is presented. It is a two-dimensional array with locally coupled chaotic elements. It offers a mechanism to escape the synchrony-desynchrony dilemma. As a result, this model has unbounded capacity of segmentation. Chaotic dynamics in the periodically driven Wilson-Cowan oscillator is analyzed by calculating the Lyapunov exponents. Computer simulations confirm the theoretical prediction
Keywords :
Lyapunov methods; chaos; image segmentation; neural nets; synchronisation; Lyapunov exponents; Wilson-Cowan oscillator; chaotic dynamics; chaotic oscillator network; neural nets; scene segmentation; synchronisation; Aerodynamics; Brain modeling; Chaos; Computer simulation; Electronic mail; Lattices; Layout; Limit-cycles; Local oscillators; Neurons;
Conference_Titel :
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-5529-6
DOI :
10.1109/IJCNN.1999.831584