A neural network model for texture discrimination

A model of texture discrimination in visual cortex was built using a feedforward network with lateral interactions among relatively realistic spiking neural elements. The elements have various membrane currents, equilibrium potentials and time constants, with action potentials and synapses. The model is derived from the modified programs of MacGregor (1987). Gabor-like filters are applied to overlapping regions in the original image; the neural network with lateral excitatory and inhibitory interactions then compares and adjusts the Gabor amplitudes in order to produce the actual texture discrimination. Finally, a combination layer selects and groups various representations in the output of the network to form the final transformed image material. We show that both texture segmentation and detection of texture boundaries can be represented in the firing activity of such a network for a wide variety of synthetic to natural images. Performance details depend most strongly on the global balance of strengths of the excitatory and inhibitory lateral interconnections. The spatial distribution of lateral connective strengths has relatively little effect. Detailed temporal firing activities of single elements in the lateral connected network were examined under various stimulus conditions. Results show (as in area 17 of cortex) that a single element's response to image features local to its receptive field can be altered by changes in the global context.

[1]  Anne Treisman,et al.  Features and objects in visual processing , 1986 .

[2]  H. Nothdurft,et al.  Texture discrimination: Representation of orientation and luminance differences in cells of the cat striate cortex , 1985, Vision Research.

[3]  M. R. Turner,et al.  Texture discrimination by Gabor functions , 1986, Biological Cybernetics.

[4]  H. C. Nothdurft,et al.  Texture segmentation and pop-out from orientation contrast , 1991, Vision Research.

[5]  A. L. Humphrey,et al.  Anatomical banding of intrinsic connections in striate cortex of tree shrews (Tupaia glis) , 1982, The Journal of comparative neurology.

[6]  S. Dehaene.  Discriminability and dimensionality effects invisual search for featural conjunctions: A functional pop-out , 1989, Perception & psychophysics.

[7]  J. P. Jones,et al.  An evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex. , 1987, Journal of neurophysiology.

[8]  T. Wiesel,et al.  Columnar specificity of intrinsic horizontal and corticocortical connections in cat visual cortex , 1989, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[9]  J. P. Jones,et al.  The two-dimensional spatial structure of simple receptive fields in cat striate cortex. , 1987, Journal of neurophysiology.

[10]  S. Grossberg,et al.  A neural network architecture for preattentive vision , 1989, IEEE Transactions on Biomedical Engineering.

[11]  J. Krüger,et al.  The connectivity underlying the orientation selectivity in the infragranular layers of monkey striate cortex , 1989, Brain Research.

[12]  T. Wiesel,et al.  Intrinsic connectivity and receptive field properties in visual cortex , 1985, Vision Research.

[13]  T. Wiesel,et al.  Clustered intrinsic connections in cat visual cortex , 1983, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[14]  W. Singer,et al.  Stimulus-specific neuronal oscillations in orientation columns of cat visual cortex. , 1989, Proceedings of the National Academy of Sciences of the United States of America.

[15]  C. Gilbert,et al.  Synaptic physiology of horizontal connections in the cat's visual cortex , 1991, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[16]  L. Maffei,et al.  The unresponsive regions of visual cortical receptive fields , 1976, Vision Research.

[17]  George L. Gerstein,et al.  Neural assemblies as building blocks of cortical computation , 1993 .

[18]  A. B. Bonds.  Role of Inhibition in the Specification of Orientation Selectivity of Cells in the Cat Striate Cortex , 1989, Visual Neuroscience.

[19]  P Perona,et al.  Preattentive texture discrimination with early vision mechanisms. , 1990, Journal of the Optical Society of America. A, Optics and image science.

[20]  M. Cynader,et al.  Intrinsic projections within visual cortex: evidence for orientation-specific local connections. , 1985, Proceedings of the National Academy of Sciences of the United States of America.

[21]  N. Hammond.  The Emergence of Maya Civilization , 1986 .

[22]  D. Mackay,et al.  Modulatory influences of moving textured backgrounds on responsiveness of simple cells in feline striate cortex , 1981, The Journal of physiology.

[23]  T. Wiesel,et al.  Relationships between horizontal interactions and functional architecture in cat striate cortex as revealed by cross-correlation analysis , 1986, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[24]  John G. Daugman,et al.  Complete discrete 2-D Gabor transforms by neural networks for image analysis and compression , 1988, IEEE Trans. Acoust. Speech Signal Process..

[25]  C. Blakemore,et al.  Lateral inhibition between orientation detectors in the cat's visual cortex , 2004, Experimental Brain Research.

[26]  Bela Julesz,et al.  A theory of preattentive texture discrimination based on first-order statistics of textons , 2004, Biological Cybernetics.

[27]  M. Porat,et al.  Localized texture processing in vision: analysis and synthesis in the Gaborian space , 1989, IEEE Transactions on Biomedical Engineering.

[28]  A. Treisman,et al.  A feature-integration theory of attention , 1980, Cognitive Psychology.

[29]  D. Sagi,et al.  Gabor filters as texture discriminator , 1989, Biological Cybernetics.

[30]  Ronald J. MacGregor,et al.  Neural and brain modeling , 1987 .

[31]  Ennio Mingolla,et al.  Neural dynamics of perceptual grouping: Textures, boundaries, and emergent segmentations , 1985 .

[32]  J. Krüger,et al.  Multimicroelectrode investigation of monkey striate cortex: spike train correlations in the infragranular layers. , 1988, Journal of neurophysiology.

[33]  Mark W. Cannon,et al.  Spatial interactions in apparent contrast: Inhibitory effects among grating patterns of different spatial frequencies, spatial positions and orientations , 1991, Vision Research.

[34]  B. Julesz.  Textons, the elements of texture perception, and their interactions , 1981, Nature.

[35]  B. Julesz,et al.  Human factors and behavioral science: Textons, the fundamental elements in preattentive vision and perception of textures , 1983, The Bell System Technical Journal.

[36]  James R. Bergen,et al.  Parallel versus serial processing in rapid pattern discrimination , 1983, Nature.