Analog VLSI For Early Vision Processes

Real time image understanding systems are required for many applications. However, early vision processes are "ill-posed" problems, these problems require extensive computational resources and thus limit the performance and speed of machine vision systems. It has been recently proposed that these problems can be solved using resistive networks. We are in the process of designing VLSI circuits which will perform edge detection and estimation of the motion field.

[1]  A. N. Tikhonov,et al.  Solutions of ill-posed problems , 1977 .

[2]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[3]  C Koch,et al.  Analog "neuronal" networks in early vision. , 1986, Proceedings of the National Academy of Sciences of the United States of America.

[4]  KochChristof,et al.  Computational vision and regularization theory , 1985 .

[5]  T. Poggio,et al.  III-Posed problems early vision: from computational theory to analogue networks , 1985, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[6]  Tomaso Poggio,et al.  Computational vision and regularization theory , 1985, Nature.