Reconstructing irregularly sampled images by neural networks  (1989)

Neural-network-like models of receptor position learning and interpolation function learning are being developed as models of how the human nervous system might handle the problems of keeping track of the receptor positions and interpolating the image between receptors. These models may also be of interest to designers of image processing systems desiring the advantages of a retina-like image sampling array.

+ Watson, Andrew

+ Ahumada, Albert

+ Yellott, John

+ Vision Science and Technology

image, networks, neural, position, processing, receptor

Conference on Human Vision, Visual Processing, and Digital Display, ed B. E. Rogowitz, Proc. Vol. 1077, pp. 228-235, SPIE, Bellingham, WA

  Ahumada_spie89.pdf (Download Acrobat Reader )
  (204KB) (application/pdf)