Skip to main content
SpringerLink
Log in

A neuromorphic architecture for cortical multilayer integration of early visual tasks

  • Published:
Machine Vision and Applications Aims and scope Submit manuscript

Abstract

The characteristics and performance of a hierarchical neural architecture, inspired by models of mammalian visual cortex, are considered. The visual pathway from sensory space to the intermediate (cortical) representation is structured in three layers, with intra and interlayer connections through feedforward and recurrent pathways. These interconnections provide a complex perceptual organization that integrates the specific functional tasks performed by each layer. This improves the capabilities of the architecture in feature extraction and segregation, further providing clues on the information content of the intermediate representation (primal sketch). Applications to preattentive vision tasks (edge and contour extractions, texture analysis and boundary completion, and defect detection) are presented with satisfactory results.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Albrecht DG, Geisler W (1991) Motion selectivity and the contrastresponse function of simple cells in the visual cortex. Vis Neurosci 7:531–546

    Google Scholar 

  2. Albus K (1975) A quantitative study of the projection area of the central and the paracentral visual field in area 17 of the cat. Exp Brain Res 24:159–202

    Google Scholar 

  3. Barlow HB (1972) Single units and sensation: a neuron doctrine for perceptual psychology? Perception 1:371–394

    Google Scholar 

  4. Baxter WT, Dow BM (1989) Horizontal organization of orientation-sensitive cells in primate visual cortex. Biol Cybern 61:171–182

    Google Scholar 

  5. Bergen JR, Landy MS (1991) Computational modeling of visual texture segregation. In: Landy MS, Movshon, JA (eds) Computational models of visual processing, MIT Press, Cambridge, MA, pp 253–271

    Google Scholar 

  6. Bisio GM, Caviglia DD, Indiveri G, Raffo L, Sabatini SP (1993) A neural network architectural model of visual cortical cells for texture segregation. Proceedings of the International Conference on Neural Networks, San Francisco Calif., pp 755–760

  7. Blasdel G (1992) Orientation, selectivity, preference, and continuity in monkey striate cortex. J Neuroscience 12:3139–3161

    Google Scholar 

  8. Bolz J, Gilbert CD (1986) Generation of end-inhibition in the visual cortex via interlaminar connections. Nature 320:362–365

    Google Scholar 

  9. Bonhoeffer T, Grinvald A (1993) The layout of iso-orientation domains in Area 18 of cat visual cortex: optical imaging reveals a pinwheel-like organization. J Neuroscience 13:4157–4180

    Google Scholar 

  10. Boser BE, Säckinger E, Bromley J, Le Cunn Y, Jackel LD (1991) An analog neural network processor with programmable topology. IEEE J Solid State Circuits 26:2017–2025

    Google Scholar 

  11. Bovik AC, Clark M, Geisler WS (1990) Multichannel texture analysis using localized spatial filters. IEEE Trans Pattern Anal Mach Intell 12:55–73

    Google Scholar 

  12. Braitenberg V, Braitenberg C (1979) Geometry of orientation columns in the visual cortex. Biol Cybern 33:179–176

    Google Scholar 

  13. Brodatz P (1966) Textures, a photographic album for artists and designers. Dover, New York

    Google Scholar 

  14. Burr DC, Morrone MC (1992) A nonlinear model of feature detection. In: Wechsler H (ed) Nonlinear vision: determination of neural receptive fields, functions, and networks. CRC Press, pp 309–328

  15. Burr DC, Morrone MC, Fiorentini A (1992) Electro-physiological investigation of edge-selective mechanisms of human vision. Vis Res 32:239–247

    Google Scholar 

  16. Burr DC, Morrone MC, Spinelli D (1989) Evidence for edge and bar detectors in human vision. Vis Res 29:419–431

    Google Scholar 

  17. Canny J (1986) A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell 8:679–698

    Google Scholar 

  18. Daugman JG (1985) Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. J Opt Soc Am A/2:1160–1169

    Google Scholar 

  19. Emerson RC, Korenberg MJ, Citron MC (1992) Identification of complex-cell intensive nonlinearities in a cascade model of cat visual cortex. Biol Cybern 66:291–300

    Google Scholar 

  20. Finkel LH, Edelman GM (1989) Integration of distribuited cortical systems by reentry: a computer simulation of interactive functionally segregated visual areas. J Neuroscience 9:3188–3208

    Google Scholar 

  21. Glezer VD, Ivanov VA, Tscherbach TA (1973) Investigation of complex and hypercomplex receptive fields of visual cortex of the cat as spatial frequency filters. Vision Res 13:1875–1904

    Google Scholar 

  22. Graham N, Beck J, Sutter A (1992) Nonlinear processes in spatial frequency channel models of perceived texture segregation: effects of sign and amount of contrast. Vision Res 32:719–743

    Google Scholar 

  23. Grossberg S, Mingolla E, Todovoric D (1989) A neural network architecture for preattentive vision. IEEE Trans Biomed Eng 36:65–83

    Google Scholar 

  24. Haralick RM (1979) Statistical and structural approaches to texture. Proc. IEEE 67:786–804

    Google Scholar 

  25. Hawken MJ, Parker AJ (1991) Spatial receptive field organization in monkey VI and its relationship to the cone mosaic. In: Landy MS, Movshon, JA (eds) Computational models of visual processing, MIT Press, Cambridge, MA, pp 83–93

    Google Scholar 

  26. Heeger DJ (1991) Nonlinear model of neural responses in cat visual cortex. In: Landy MS, Movshon, JA (eds) Computational models of visual processing. MIT Press, Cambridge, MA, pp 119–133

    Google Scholar 

  27. Hubel DH, Wiesel TN (1962) Receptive fields, binocular interaction and functional architecture in the cat's visual cortex. J Physiol 160:106–154

    Google Scholar 

  28. Hubel DH, Wiesel TN (1965) Receptive fields and functional architecture in the two nonstriate visual areas (18 and 19) of the cat. J Neurophysiol 160:106–154

    Google Scholar 

  29. Jain AK, Farrokhnia F (1991) Unsupervised texture segmentation using Gabor filters. Patt Recogn 24:1167–1186

    Google Scholar 

  30. Jones J, Palmer L (1987) An evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex. J Neurophysiol 58:1233–1258

    Google Scholar 

  31. Julesz B (1981) Textons, the elements of texture perception and their interactions. Nature 290:91–97

    Google Scholar 

  32. Kobayashi H, White JL, Abidi AA (1991) An active resistor network for Gaussian filtering of images. IEEE J Solid State Circuits 26:738–748

    Google Scholar 

  33. Kulikowski JJ, Bishop PO (1981) Linear analysis of the responses of simple cells in the cat visual cortex. Exp Brain Res 44:386–400

    Google Scholar 

  34. Malik J, Perona P (1990) Preattentive texture discrimination with early vision mechanisms. J Opt Soc Am 7:923–932

    Google Scholar 

  35. Manjunath BS, Chellappa R (1993) A unified approach to boundary perception: edges, textures and illusory contours. IEEE Trans Neural Networks 4:96–107

    Google Scholar 

  36. Marr D (1982) Vision. Freeman, New York

    Google Scholar 

  37. Mead CA (1989) Analog VLSI and neural systems. Addison-Wesley, Reading

    Google Scholar 

  38. Obermayer K, Blasdel GG (1993) Geometry of orientation and ocular dominance columns in monkey striate cortex. J Neuroscience 13:4114–4129

    Google Scholar 

  39. Perona P, Malik J (1990) Detecting and localizing edges composed of steps, peaks and roofs. Proceedings of the International Conference on Computer Vision, Osaka, pp 52–57

  40. Raffo L, Sabatini SP, Caviglia DD, Bisio GM (1993) Anisotropic active resistor meshes for implementing image processing operators. Electronic Lett 29:960–961

    Google Scholar 

  41. Raffo L, Sabatini SP, Indiveri G, Nateri G, Bisio GM (1994) A memory-based recurrent neural architecture for chips emulating cortical visual processing. IEICE Trans Electronics E77-C, pp 1065–1074

    Google Scholar 

  42. Satyanarayana S, Tsividis PY, Graf PH (1992) A reconfigurable VLSI neural network. IEEE J Solid State Circuits 27:67–81

    Google Scholar 

  43. Schwartz EL (1980) Computational anatomy and functional architecture of striate cortex: a spatial mapping approach to perceptual coding. Vis Res 20:645–669

    Google Scholar 

  44. Skottun BC, De Valois RL, Grosof DH, Movshon JA, Albrecht DG, Bonds AB (1991) Classifying simple and complex cells on the basis of response modulation. Vis Res 31:1079–1086

    Google Scholar 

  45. Turner MR (1986) Texture discrimination by Gabor functions. Biol Cybern 55:71–82

    Google Scholar 

  46. Van Essen DC, Anderson CH, Felleman DJ (1992) Information processing in the primate visual system — an integrated systems perspective. Science 255:419–423

    Google Scholar 

  47. Von der Heydt R, Peterhans E (1989) Cortical contour mechanisms and geometrical illusions. In: Lam DM-K Gilbert CD (ed) Neural mechanisms of visual perception. MIT Press, Portfollo Publishing Company, The Woodlands, TX, pp 157–170

    Google Scholar 

  48. Von der Heydt R, Peterhans E (1989) Mechanisms of contour perception in monkey visual cortex. I. Lines of pattern discontinuity. J Neurosci 9:1731–1748

    Google Scholar 

  49. Wörgötter F, Koch C (1991) A detailed model of the primary vision pathway in the cat: comparison of afferrent excitatory and intracortical inhibitory connection schemes for orientation selectivity. J Neurosci 11:1959–1979

    Google Scholar 

  50. Wörgötter F, Niebur E, Koch C (1991) Isotropic connections generate functional asymmetrical behavior in visual cortical cells. J Neurophysiol 66:444–459

    Google Scholar 

  51. Young RA (1986) The Gaussian derivative theory of spatial vision: visual cortex simulation. Technical Report GMR-5323, General Motors Research, USA

    Google Scholar 

  52. Young RA, Lesperance RM (1993) A physiological model of motion analysis for machine vision. Technical Report GMR-7878, General Motors Research, USA

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Biophysical and Electronic Engineering, University of Genova, Via Opera Pia 11/A, I-16145, Genova, Italy

    Giacomo Indiveri, Silvio P. Sabatini & Giacomo M. Bisio

  2. Institute of Electrical Engineering, University of Cagliari, Piazza d'Armi, I-09123, Cagliari, Italy

    Luigi Raffo

Authors
  1. Giacomo Indiveri
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Luigi Raffo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Silvio P. Sabatini
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Giacomo M. Bisio
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Indiveri, G., Raffo, L., Sabatini, S.P. et al. A neuromorphic architecture for cortical multilayer integration of early visual tasks. Machine Vis. Apps. 8, 305–314 (1995). https://doi.org/10.1007/BF01211491

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF01211491

Key words

Search

Navigation