A recurrent neural architecture mimicking cortical preattentive vision systems

Abstract Low- and intermediate-level tasks of visual perception are based on multiple and cooperating simple agent architectures, made up of networks of formal neurons organized into a three-layer neural network locally connected. In each layer, there is a specific intermediate representation of the image: the first layer extracts oriented feature elements; the second and third ones are used to control and coordinate interactions among features. Inter- and intra-layer recurrent connections are responsible for the integration of the different computational tasks performed by each neuron into a non-local percept. The output of cortical neurons also depends on the excitation of neighboring neurons. Applications to texture discrimination in both natural and artificial textures are presented.

[1]  R. von der Heydt,et al.  Mechanisms of contour perception in monkey visual cortex. I. Lines of pattern discontinuity , 1989, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[2]  V. Glezer,et al.  Investigation of complex and hypercomplex receptive fields of visual cortex of the cat as spatial frequency filters. , 1973, Vision research.

[3]  H B Barlow,et al.  Single units and sensation: a neuron doctrine for perceptual psychology? , 1972, Perception.

[4]  Michael S. Landy,et al.  Computational models of visual processing , 1991 .

[5]  A. Grinvald,et al.  The layout of iso-orientation domains in area 18 of cat visual cortex: optical imaging reveals a pinwheel-like organization , 1993, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[6]  David C. Burr,et al.  A non-linear model of feature detection. , 1992 .

[7]  J. L. White,et al.  An active resistor network for Gaussian filtering of images , 1991 .

[8]  A. B. Bonds,et al.  Classifying simple and complex cells on the basis of response modulation , 1991, Vision Research.

[9]  A. B. Bonds.  Dual Inhibitory Mechanisms for Definition of Receptive Field Characteristics in a Cat Striate Cortex , 1991, NIPS.

[10]  F. Crick.  Function of the thalamic reticular complex: the searchlight hypothesis. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[11]  J. Bergen,et al.  Computational Modeling of Visual Texture Segregation , 1991 .

[12]  Daniele D. Caviglia,et al.  A neural network architectural model of visual cortical cells for texture segregation , 1993, IEEE International Conference on Neural Networks.

[13]  D. G. Albrecht,et al.  Motion selectivity and the contrast-response function of simple cells in the visual cortex , 1991, Visual Neuroscience.

[14]  L. Finkel,et al.  Integration of distributed cortical systems by reentry: a computer simulation of interactive functionally segregated visual areas , 1989, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[15]  D H HUBEL,et al.  RECEPTIVE FIELDS AND FUNCTIONAL ARCHITECTURE IN TWO NONSTRIATE VISUAL AREAS (18 AND 19) OF THE CAT. , 1965, Journal of neurophysiology.

[16]  D Ferster,et al.  Nonlinearity of spatial summation in simple cells of areas 17 and 18 of cat visual cortex. , 1991, Journal of neurophysiology.

[17]  David C. Burr,et al.  Electro-physiological investigation of edge-selective mechanisms of human vision , 1992, Vision Research.

[18]  Carver A. Mead,et al.  Neuromorphic electronic systems , 1990, Proc. IEEE.

[19]  Michael J. Hawken,et al.  Spatial receptive field organization in monkey V1 and its relationship to the cone mosaic , 1991 .

[20]  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.

[21]  Klein,et al.  Nonlinear directionally selective subunits in complex cells of cat striate cortex. , 1987, Journal of neurophysiology.

[22]  Rama Chellappa,et al.  A unified approach to boundary perception: edges, textures, and illusory contours , 1993, IEEE Trans. Neural Networks.

[23]  Kunihiko Fukushima,et al.  Neural Networks for Visual Pattern Recognition , 1991 .

[24]  R. B. Pinter,et al.  Nonlinear Vision: Determination of Neural Receptive Fields, Function, and Networks , 1992 .

[25]  D. Hubel,et al.  Receptive fields, binocular interaction and functional architecture in the cat's visual cortex , 1962, The Journal of physiology.

[26]  Daniele D. Caviglia,et al.  Anisotropic active resistor meshes for implementing image processing operators , 1993 .

[27]  D. Burr,et al.  Evidence for edge and bar detectors in human vision , 1989, Vision Research.

[28]  Takayuki Ito,et al.  Neocognitron: A neural network model for a mechanism of visual pattern recognition , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[29]  Phil Brodatz,et al.  Textures: A Photographic Album for Artists and Designers , 1966 .

[30]  R M Douglas,et al.  Position-specific adaptation in simple cell receptive fields of the cat striate cortex. , 1991, Journal of neurophysiology.

[31]  I. Ohzawa,et al.  Spatiotemporal organization of simple-cell receptive fields in the cat's striate cortex. II. Linearity of temporal and spatial summation. , 1993, Journal of neurophysiology.

[32]  T. Wiesel.  Neural Mechanisms of Visual Perception , 1997 .

[33]  Carver Mead,et al.  Analog VLSI and neural systems , 1989 .

[34]  A. B. Bonds,et al.  Inhibitory refinement of spatial frequency selectivity in single cells of the cat striate cortex , 1991, Vision Research.

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

[36]  D. Heeger.  Nonlinear model of neural responses in cat visual cortex. , 1991 .

[37]  K. Albus.  A quantitative study of the projection area of the central and the paracentral visual field in area 17 of the cat , 1975, Experimental brain research.

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

[39]  C. Gilbert,et al.  Generation of end-inhibition in the visual cortex via interlaminar connections , 1986, Nature.

[40]  L. Palmer,et al.  The two-dimensional spatial structure of nonlinear subunits in the receptive fields of complex cells , 1990, Vision Research.