Using Visual Latencies to Improve Image Segmentation

An artificial neural network model is proposed that combines several aspects taken from physiological observations (oscillations, synchronizations) with a visual latency mechanism in order to achieve an improved analysis of visual scenes. The network consists of two parts. In the lower layers that contain no lateral connections the propagation velocity of the activity of the units depends on the contrast of the individual objects in the scene. In the upper layers lateral connections are used to achieve synchronization between corresponding image parts. This architecture assures that the activity that arises in response to a scene containing objects with different contrast is spread out over several layers in the network. Thereby adjacent objects with different contrast will be separated and synchronization occurs in the upper layers without mutual disturbance between different objects. A comparison with a one-layer network shows that synchronization in the latency dependent multilayer net is indeed achieved much faster as soon as more than five objects have to be recognized. In addition, it is shown that the network is highly robust against noise in the stimuli or variations in the propagation delays (latencies), respectively. For a consistent analysis of a visual scene the different features of an individual object have to be recognized as belonging together and separated from other objects. This study shows that temporal differences, naturally introduced by stimulus latencies in every biological sensory system, can strongly improve the performance and allow for an analysis of more complex scenes.

[1]  W. Levick.  Variation in the response latency of cat retinal ganglion cells. , 1973, Vision research.

[2]  H. Wässle,et al.  Response latency of brisk‐sustained (X) and brisk‐transient (Y) cells in the cat retina , 1982, The Journal of physiology.

[3]  S. Whittaker,et al.  Origin of wavelets in the visual evoked potential. , 1983, Electroencephalography and clinical neurophysiology.

[4]  J. T. Enright.  On pulfrich-illusion eye movements and accommodation vergence during visual pursuit , 1985, Vision Research.

[5]  K. Kratz,et al.  Visual latency of ganglion X- and Y-cells: A comparison with geniculate X- and Y-cells , 1987, Vision Research.

[6]  G. Edelman,et al.  Reentrant signaling among simulated neuronal groups leads to coherency in their oscillatory activity. , 1989, Proceedings of the National Academy of Sciences of the United States of America.

[7]  G. Orban,et al.  Response latencies of visual cells in macaque areas V1, V2 and V5 , 1989, Brain Research.

[8]  R. Freeman,et al.  A physiological correlate of the pulfrich effect in cortical neurons of the cat , 1989, Vision Research.

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

[10]  S. Strogatz,et al.  Synchronization of pulse-coupled biological oscillators , 1990 .

[11]  T. Pun,et al.  Figure-ground separation: evidence for asynchronous processing in visual perception? , 1991 .

[12]  C. Koch,et al.  A detailed model of the primary visual pathway in the cat: comparison of afferent excitatory and intracortical inhibitory connection schemes for orientation selectivity , 1991, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[13]  B J Richmond,et al.  Concurrent processing and complexity of temporally encoded neuronal messages in visual perception. , 1991, Science.

[14]  G. Edelman,et al.  Reentry and the problem of integrating multiple cortical areas: simulation of dynamic integration in the visual system. , 1992, Cerebral cortex.

[15]  C. Koch,et al.  An oscillation-based model for the neuronal basis of attention , 1993, Vision Research.

[16]  D. V. van Essen,et al.  A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information , 1993, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[17]  A. Aertsen.  Brain theory : spatio-temporal aspects of brain function , 1993 .

[18]  R. Eckhorn,et al.  High frequency (60-90 Hz) oscillations in primary visual cortex of awake monkey. , 1993, Neuroreport.

[19]  Winfried A. Fellenz,et al.  A Sequential Model for Attentive Object Selection , 1994 .

[20]  Thierry Pun,et al.  Asynchrony in image analysis: using the luminance-to-response-latency relationship to improve segmentation , 1994 .

[21]  D. Burr,et al.  Selective suppression of the magnocellular visual pathway during saccadic eye movements , 1994, Nature.

[22]  M. Posner,et al.  Attentional networks , 1994, Trends in Neurosciences.

[23]  H. Dinse,et al.  The timing of processing along the visual pathway in the cat. , 1994, Neuroreport.

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

[25]  Christof Koch,et al.  Control of Selective Visual Attention: Modeling the Where Pathway , 1995, NIPS.

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

[27]  R. Desimone,et al.  Neural mechanisms of selective visual attention. , 1995, Annual review of neuroscience.

[28]  S. Nelson,et al.  An emergent model of orientation selectivity in cat visual cortical simple cells , 1995, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[29]  W Singer,et al.  Visual feature integration and the temporal correlation hypothesis. , 1995, Annual review of neuroscience.

[30]  F. Wörgötter,et al.  Utilizing latency for object recognition in real and artificial neural networks , 1996, Neuroreport.

[31]  K. Funke,et al.  On the significance of temporally structured activity in the dorsal lateral geniculate nucleus (LGN) , 1997, Progress in Neurobiology.

[32]  Florentin Wörgötter,et al.  Introducing visual latencies into spin-lattice models for image segmentation: a neuromorphic approach to a computer vision problem , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).