DocumentCode :
3127572
Title :
Parallel distributed networks for image smoothing and segmentation in analog VLSI
Author :
Lumsdaine, A. ; Wyatt, J. ; Elfadel, I.
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., MIT, Cambridge, MA, USA
fYear :
1989
fDate :
13-15 Dec 1989
Firstpage :
272
Abstract :
Consideration is given to switched linear resistive networks and nonlinear resistive networks for image smoothing and segmentation problems in robot vision. The latter network type is derived from the former by way of an intermediate stochastic formulation, and a new result relating the solution sets of the two is given for the so-called zero-temperature limit. The authors present simulation studies of several continuation methods that can be gracefully implemented in analog VLSI and that seem to given good results for these nonconvex optimization problems
Keywords :
VLSI; analogue computer circuits; computer vision; parallel architectures; analog VLSI; analogue computer circuits; computer vision; image smoothing; nonconvex optimization; nonlinear resistive networks; parallel architectures; parallel distributed networks; robot vision; segmentation; switched linear resistive networks; zero-temperature limit; Computer science; Computer vision; Image segmentation; Intelligent networks; Laboratories; Minimization methods; Robot vision systems; Smoothing methods; Stochastic processes; Very large scale integration;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Decision and Control, 1989., Proceedings of the 28th IEEE Conference on
Conference_Location :
Tampa, FL
Type :
conf
DOI :
10.1109/CDC.1989.70116
Filename :
70116
Link To Document :
بازگشت