Feature discovery on segmented objects in SAR imagery using self-organizing neural networks

Conference · Wed Jan 01 00:00:00 EST 1992

OSTI ID:6598113

Fogler, R J; Koch, M W; Moya, M M ^[1]; Hush, D R ^[2]

---

1. Sandia National Labs., Albuquerque, NM (United States)
2. New Mexico Univ., Albuquerque, NM (United States). Dept. of Electrical and Computer Engineering

In this paper we investigate the applicability of the feature extraction mechanisms found in the neurophysiology of mammals to the problem of object recognition in synthetic aperture radar imagery. Our approach is to present multiple views of objects to be recognized to a two-stage self-organizing neural network architecture. The first stage, a two-layer Neocognitron, performs feature extraction in each layer The resulting feature vectors are presented to the second stage, an ART-2A classifier self-organizing neural network which clusters the features into multiple object categories. The feature extraction operators resulting from the self-organization process are compared to the feature extraction mechanisms found in the neurophysiology of vision. In a previous paper, the Neocognitron was trained on raw SAR imagery. The architecture was able to recognize a simulated vehicle at arbitrary azimuthal orientations at a single depression angle while rejecting clutter as well as other vehicles. Feature extraction on raw imagery yielded features that were robust but very difficult to interpret. In this paper we report the results of some new experiments in which the self-organization process is applied separately to shadow and bright returns from objects to be recognized. Feature extraction on shadow returns yield oriented contrast edge operators suggestive of bipartite simple cells observed in the striate cortex of mammals. Feature extraction on the specularity patterns in bright returns yield a collection of operators resembling a twodimensional Haar basis set. We compare the performance of the earlier two-stage neural network trained on raw imagery with a modified network using the new feature set.

• Research Organization: Sandia National Labs., Albuquerque, NM (United States)
• Sponsoring Organization: USDOE; USDOE, Washington, DC (United States)
• DOE Contract Number: AC04-76DP00789
• OSTI ID: 6598113
• Report Number(s): SAND-92-2086C; CONF-930445-1; ON: DE93010685
• Resource Relation: Conference: Society of Photo-Optical Instrumentation Engineers (SPIE) OE/aerospace science and sensing meeting, Orlando, FL (United States), 11-16 Apr 1993
• Country of Publication: United States
• Language: English

Related Subjects

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEFENSE
99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE
NEURAL NETWORKS
MATHEMATICAL MODELS
SYNTHETIC-APERTURE RADAR
IMAGE PROCESSING
PATTERN RECOGNITION
RETINA
VISION
BODY
BODY AREAS
EYES
FACE
HEAD
MEASURING INSTRUMENTS
ORGANS
PROCESSING
RADAR
RANGE FINDERS
SENSE ORGANS
450000* - Military Technology
Weaponry
& National Defense
990200 - Mathematics & Computers