Segmentation Circuits Using Constrained Optimization

Part of Advances in Neural Information Processing Systems 4 (NIPS 1991)

Bibtex Metadata Paper

Authors

John Harris

Abstract

A novel segmentation algorithm has been developed utilizing an absolute(cid:173) value smoothness penalty instead of the more common quadratic regu(cid:173) larizer. This functional imposes a piece-wise constant constraint on the segmented data. Since the minimized energy is guaranteed to be convex, there are no problems with local minima and no complex continuation methods are necessary to find the unique global minimum. By interpret(cid:173) ing the minimized energy as the generalized power of a nonlinear resistive network, a continuous-time analog segmentation circuit was constructed.