Share Email Print

Proceedings Paper

Analog neural networks for focal-plane image processing
Author(s): Bimal P. Mathur; Shih-Chi Liu; H. Taichi Wang
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Autonomous systems have to overcome two major problems in interpreting the data collected by sensors. These problems are due to the fact that multiple real world scenes can produce a given intensity distribution and that sensor data is often corrupted by noise. These problems can be solved by imposing certain a priori knowledge about the world to arrive at a unique solution. This reduces early vision problems to constrained optimization problems, which can be conveniently formulated as energy minimization problems in the framework of Regularization Theory. These energy functions can be implemented in analog hardware. This feature makes this approach very attractive for real time autonomous systems. We are presently developing algorithms and analog CMOS chips based on this approach for focal plane image processing.

Paper Details

Date Published: 1 July 1990
PDF: 11 pages
Proc. SPIE 1242, Charge-Coupled Devices and Solid State Optical Sensors, (1 July 1990); doi: 10.1117/12.19446
Show Author Affiliations
Bimal P. Mathur, Rockwell International Science Ctr. (United States)
Shih-Chi Liu, Rockwell International Science Ctr. (United States)
H. Taichi Wang, Rockwell International Science Ctr. (United States)

Published in SPIE Proceedings Vol. 1242:
Charge-Coupled Devices and Solid State Optical Sensors
Morley M. Blouke, Editor(s)

© SPIE. Terms of Use
Back to Top