Pulse-coupled neural networks for contour and motion matchings

Two neural networks based on temporal coding are proposed in this paper to perform contour and motion matchings. Both of the proposed networks are three-dimensional (3D) pulse-coupled neural networks (PCNNs). They are composed of simplified Eckhorn neurons and mimic the structure of the primary visual cortex. The PCNN for contour matching can segment from the background the object with a particular contour, which has been stored as prior knowledge and controls the network activity in the form of spike series; The PCNN for motion matching not only detects the motion in the visual field, but also extracts the object moving in an arbitrarily specified direction. The basic idea of these two models is to encode information into the timing of spikes and later to decode this information through coincidence detectors and synapse delays to realize the knowledge-controlled object matchings. The simulation results demonstrate that the temporal coding and the decoding mechanisms are powerful enough to perform the contour and motion matchings.

[1]  Jean-Cédric Chappelier,et al.  RST: A Connectionist Architecture to Deal with Spatiotemporal Relationships , 1998, Neural Computation.

[2]  Heggere S. Ranganath,et al.  Perfect image segmentation using pulse coupled neural networks , 1999, IEEE Trans. Neural Networks.

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

[4]  John L. Johnson,et al.  PCNN models and applications , 1999, IEEE Trans. Neural Networks.

[5]  R. Weale.  Vision. A Computational Investigation Into the Human Representation and Processing of Visual Information. David Marr , 1983 .

[6]  DeLiang Wang,et al.  Scene analysis by integrating primitive segmentation and associative memory , 2002, IEEE Trans. Syst. Man Cybern. Part B.

[7]  W. Singer,et al.  Oscillatory Neuronal Responses in the Visual Cortex of the Awake Macaque Monkey , 1992, The European journal of neuroscience.

[8]  Zhaoping Li,et al.  A Neural Model of Contour Integration in the Primary Visual Cortex , 1998, Neural Computation.

[9]  Mark E. Oxley,et al.  Physiologically motivated image fusion for object detection using a pulse coupled neural network , 1999, IEEE Trans. Neural Networks.

[10]  S. Ullman.  The Interpretation of Visual Motion , 1979 .

[11]  Christoph von der Malsburg,et al.  The Correlation Theory of Brain Function , 1994 .

[12]  R. Eckhorn,et al.  Coherent oscillations: A mechanism of feature linking in the visual cortex? , 1988, Biological Cybernetics.

[13]  J. J. Hopfield,et al.  Pattern recognition computation using action potential timing for stimulus representation , 1995, Nature.

[14]  Bo Yu,et al.  Pulse coupled neural network for motion detection , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[15]  Ali A. Minai,et al.  Detecting corresponding segments across images using synchronizable pulse-coupled neural networks , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

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

[17]  Reinhard Eckhorn,et al.  Feature Linking via Synchronization among Distributed Assemblies: Simulations of Results from Cat Visual Cortex , 1990, Neural Computation.

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

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

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

[21]  A. Damasio.  Time-locked multiregional retroactivation: A systems-level proposal for the neural substrates of recall and recognition , 1989, Cognition.