Accession Number:

ADA234936

Title:

Artificial Neural System for Object Classification and Orientation Estimation

Descriptive Note:

Contractor rept.

Corporate Author:

ARMY ARMAMENT RESEARCH DEVELOPMENT AND ENGINEERING CENTER PICATINNY ARSENAL NJ FIRE SUPPORT ARMAMENT CENTER

Report Date:

1991-04-01

Pagination or Media Count:

64.0

Abstract:

The usefulness of self-organizing neural systems for the problems of object recognition and orientation estimation are discussed. Self-organizing neural systems, like unsupervised cluster algorithms from classical pattern recognition, are most useful when no predetermined labels are available to attach to input patterns which must be categorized by the system. However, this makes it necessary to assign a natural category to the input stimuli from the environment. Only with some type of supervisory feedback will this natural category be associated with the proper label for the input pattern. Without this teaching input, the internal, self-organizing principles of the system must be used to assign categories. These assigned categories may or may not coincide with the unique labels of an external supervisory system.

Subject Categories:

  • Military Aircraft Operations
  • Cybernetics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE