Design of a Multitask Neurovision Processor
The architecture of a biologically motivated visual-information processor that can perform a variety of tasks associated with the early stages of machine vision is described. The computational operations performed by the processor emulate the spatiotemporal information-processing capabilities of certain neural-activity fields found along the human visual pathway. The state-space model of the neurovision processor is a two-dimensional nural network of densely interconnected nonlinear processing elements PE’s. An individual PE represents the dynamic activity exhibited by a spatially localized population of excitatory and inhibitory nerve cells. Each PE may receive inputs from an external signal space as well as from the neighboring PE’s within the network. The information embedded within the signal space is extracted by the feedforward subnet. The feedback subnet of the neurovision processor generates useful steady-state and temporal-response characteristics that can be used for spatiotemporal filtering, short-term visual memory, spatiotemporal stabilization, competitive feedback interaction, and content-addressable memory. To illustrate the versatility of the multitask processor design for machine-vision applications, a computer simulation of a simplified vision system for filtering, storing, and classifying noisy gray-level images is presented.
Key wordsneural-activity field neuro-vision processor spatio-temporal processing short-term visual memory spatio-temporal stabilization content addressable memory
Unable to display preview. Download preview PDF.
- 2.L. Uhr, “Psychological motivation and underlying concepts, ” in Structured Computer Vision, S. Tanimoto and A. Klinger, (eds.), Academic Press: New York, 1980, pp. 1–30.Google Scholar
- 3.S.P. Levitan, C.C. Weems, A.R. Hanson, and E.H. Riseman, “The UMass image understanding architecture,” in Parallel Computer Vision, L. Uhr,ed., Academic Press: New York pp. 215–248.1987Google Scholar
- 6.M.M. Gupta and G.K. Knopf, “A multi-task neuro-vision processor with extensive feedback and feedforward connections,” in Image Processing, K.-H. Taou, ed., Proc. Soc. Photo-Opt. Instrum. Eng., vol 1606, pp. 482–495, 1991.Google Scholar
- 8.G.K. Knopf, “Theoretical studies of a dynamic neurovision processor with a biologically motivated design,” Ph.D. dissertation, University of Saskatchewan, Canada, 1991.Google Scholar
- 11.P.K. Simpson, Artificial Neural Systems, Pergamon Press: New York, 1991.Google Scholar
- 14.M.D. Levine, Vision in Man and Machine, McGraw-Hill: New York, 1985.Google Scholar
- 15.L. Uhr, “Highly parallel, hierarchical, recognition cone perceptual structures,” in Parallel Computer Vision, L. Uhr, ed., Academic Press: New York: 1987, pp. 249–292.Google Scholar