Biomorphic Networks for ATR and Higher-Level Processing.
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 network's 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.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 10, 1998
- Accession Number
- ADA347722
Entities
People
- Nabil H. Farhat
Organizations
- Moore School of Electrical Engineering