Accession Number:

ADA347722

Title:

Biomorphic Networks for ATR and Higher-Level Processing.

Descriptive Note:

Quarterly rept. no. 4, 1 Apr-1 Jul 98,

Corporate Author:

MOORE SCHOOL OF ELECTRICAL ENGINEERING PHILADELPHIA PA DEPT OF ELECTRICAL ENGINEERING AND SCIENCE

Personal Author(s):

Report Date:

1998-01-10

Pagination or Media Count:

27.0

Abstract:

Invariant features in two dimensional binary images are extracted in a single layer network of locally coupled spiking pulsating model neurons with prescribed synapto dendritic response. The feature vector for an image is represented as invariant structure in the aggregate histogram of interspike intervals obtained by computing time intervals between successive spikes produced from each neuron over a given period of time and combining such intervals from all neurons in the network into a histogram. Simulation results show that the feature vectors are more pattern specific and invariant under translation, rotation, and change in scale or intensity than achieved in earlier work. We also describe an application of such networks to segmentation of line edge enhanced or silhouette images. The biomorphic spiking networks capabilities in segmentation and invariant feature extraction may prove to be, when they are combined, valuable in Automated Target Recognition ATR and other automated object recognition systems.

Subject Categories:

  • Cybernetics
  • Bionics
  • Target Direction, Range and Position Finding

Distribution Statement:

APPROVED FOR PUBLIC RELEASE