Accession Number:

ADA238252

Title:

Invariant Target Recognition Using Self-Organizing Networks

Descriptive Note:

Final rept.,

Corporate Author:

NAVAL SURFACE WARFARE CENTER DAHLGREN VA

Personal Author(s):

• Farrar, Beth
• Farsaie, Ali
• Fuller, J. J.

Report Date:

1990-10-01

Pagination or Media Count:

30.0

Abstract:

This paper presents an overview of neural network technology and specifics of the self-organizing networks. An artificial neural network is described which recognizes objects regardless of their spatial orientation. This network is invariant to rotation, scale, and translation. Invariance is built into the network by introducing a unique set of features which were developed in-house. This overcame the two shortcomings of long training times and combinatorial explosion of terms often present in other networks. Preliminary results suggest that with further refinement and enhancement, the system described in this report will have the capability to reliably recognize targets under adverse environmental conditions.

Descriptors:

• *SPATIAL DISTRIBUTION
• TRAINING
• NETWORKS
• TARGET RECOGNITION
• SELF ORGANIZING SYSTEMS
• ORIENTATION(DIRECTION)
• ADVERSE CONDITIONS
• COMBINATORIAL ANALYSIS
• INVARIANCE
• ROTATION
• NEURAL NETS
• EXPLOSIONS

Subject Categories:

• Cybernetics
• Target Direction, Range and Position Finding

Distribution Statement:

APPROVED FOR PUBLIC RELEASE