Accession Number:

ADA278124

Title:

Correlation Filter Synthesis Using Neural Networks.

Descriptive Note:

Final technical rept. Jun 91-Apr 93,

Corporate Author:

DAYTON UNIV OH RESEARCH INST

Personal Author(s):

• Gustafson, Steven C.
• Flannery, David L.

Report Date:

1993-12-01

Pagination or Media Count:

173.0

Abstract:

Excellent results were obtained using neural networks to synthesize filters for optical correlators, including filters for both cluttered backgrounds and target rotation angles not used in training. The most significant results employed new stretch and hammer neural networks which constitute an important and enduring advance because they train with guaranteed upper bounds on computational effort and generalize with guaranteed lower bounds on smoothness and stability. These results indicate good prospects for training neural networks to synthesize filters for a wide range of target distortions, and this approach has clear advantages compared to searching stored filters. Neural networks, Optical pattern recognition, Optimizing algorithms, Target recognition.

Descriptors:

• *NEURAL NETS
• *SYNTHESIS
• *TARGET RECOGNITION
• *OPTICAL CORRELATORS
• *OPTICAL DETECTORS
• ALGORITHMS
• COMPUTERIZED SIMULATION
• BACKGROUND
• OPTICAL TRACKING
• LIGHT MODULATORS
• ROTATION
• PATTERN RECOGNITION
• TARGETS
• OPTIMIZATION
• TRAINING
• ANGLES
• STABILITY

Subject Categories:

• Optical Detection and Detectors

Distribution Statement:

APPROVED FOR PUBLIC RELEASE