Pixel clustering by adaptive pixel moving and chaotic synchronization

In this paper, a network of coupled chaotic maps for pixel clustering is proposed. Time evolutions of chaotic maps in the network corresponding to a pixel cluster are synchronized with each other. Those synchronized trajectories are desynchronized with respect to the time evolutions of chaotic maps corresponding to other pixel clusters in the same image. A pixel motion mechanism is also introduced, which makes each group of pixels more compact and, consequently, makes the model robust enough to classify ambiguous pixels. Another feature of the proposed model is that the number of pixel clusters does not need to be previously known.

[1]  Hansel,et al.  Synchronization and computation in a chaotic neural network. , 1992, Physical review letters.

[2]  Nizam Omar,et al.  Locally coupled chaotic oscillator network for scene segmentation , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[3]  K. Kaneko.  Clustering, coding, switching, hierarchical ordering, and control in a network of chaotic elements , 1990 .

[4]  Nizam Omar,et al.  Scene Segmentation of the Chaotic oscillator Network , 2000, Int. J. Bifurc. Chaos.

[5]  Peter König,et al.  Binding by temporal structure in multiple feature domains of an oscillatory neuronal network , 1994, Biological Cybernetics.

[6]  DeLiang Wang,et al.  Range image segmentation using a relaxation oscillator network , 1999, IEEE Trans. Neural Networks.

[7]  Paul Wintz,et al.  Digital image processing (2nd ed.) , 1987 .

[8]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[9]  W. Singer,et al.  Oscillatory responses in cat visual cortex exhibit inter-columnar synchronization which reflects global stimulus properties , 1989, Nature.

[10]  Anil K. Jain,et al.  Algorithms for Clustering Data , 1988 .

[11]  E. Fetz,et al.  Coherent 25- to 35-Hz oscillations in the sensorimotor cortex of awake behaving monkeys. , 1992, Proceedings of the National Academy of Sciences of the United States of America.

[12]  Ke Chen,et al.  Perceiving spirals and inside/outside relations by a neural oscillator network , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[13]  DeLiang Wang,et al.  Image Segmentation Based on Oscillatory Correlation , 1997, Neural Computation.

[14]  DeLiang Wang,et al.  Perceiving geometric patterns: from spirals to inside-outside relations , 2001, IEEE Trans. Neural Networks.

[15]  Deliang Wang,et al.  Global competition and local cooperation in a network of neural oscillators , 1995 .

[16]  Liang Zhao,et al.  A network of dynamically coupled chaotic maps for scene segmentation , 2001, IEEE Trans. Neural Networks.

[17]  Yuming Chen,et al.  Global stability of neural networks with distributed delays , 2002, Neural Networks.

[18]  Hichem Frigui,et al.  Self-Organization of Pulse-Coupled Oscillators with Application to Clustering , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  Guy J. Brown,et al.  Separation of speech from interfering sounds based on oscillatory correlation , 1999, IEEE Trans. Neural Networks.

[20]  DeLiang Wang,et al.  A dynamically coupled neural oscillator network for image segmentation , 2002, Neural Networks.

[21]  Xiuwen Liu,et al.  Range Image Segmentation Using a LEGION Network , 1996 .

[22]  Ch. von der Malsburg,et al.  A neural cocktail-party processor , 1986, Biological Cybernetics.

[23]  DeLiang Wang,et al.  Motion segmentation based on motion/brightness integration and oscillatory correlation , 2000, IEEE Trans. Neural Networks Learn. Syst..