Visual image processing by way of neural nets with nonlocal ties
N. S. Belliustin, Alexander Gennadievich Khobotov · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 1994
This investigation is one of the preliminary steps to create an artificial system of visual image recognition and reconstruction implementing main principles of visual image processing in living biological systems. A previous study of neural net models with decreasing inner neurons' dynamics proved that net with lateral inhibition ties is able to convert image into compressed form and to pick out key elements of the picture. The present papers propose to use a reverse neural net with increasing inner neurons' dynamics with the same other parameters (the conjugate net) for image back reconstruction and image histograms' entropy measures as integral values for dynamic image processing monitoring and control.