A concurrent neural module classifier for automated target recognition in SAR imagery

Authors:
Victor-Emil Neagoe;Daniel-Cris Carausu;Gabriel-Eduard Strugaru
Affiliations:
Depart. Electronics, Telecommunications & Information Technology, Polytechnic University of Bucharest, Bucharest, Romania;Depart. Electronics, Telecommunications & Information Technology, Polytechnic University of Bucharest, Bucharest, Romania;Depart. Electronics, Telecommunications & Information Technology, Polytechnic University of Bucharest, Bucharest, Romania
Venue:
ICCOMP'10 Proceedings of the 14th WSEAS international conference on Computers: part of the 14th WSEAS CSCC multiconference - Volume I
Year:
2010

Citing 4
Cited 0

Self-Organizing Maps

Self-Organizing Maps
Concurrent Self-Organizing Maps for Pattern Classification

ICCI '02 Proceedings of the 1st IEEE International Conference on Cognitive Informatics
Simple Gabor feature space for invariant object recognition

Pattern Recognition Letters
Pattern Recognition and Machine Learning (Information Science and Statistics)

Pattern Recognition and Machine Learning (Information Science and Statistics)

Quantified Score

Hi-index	0.00

Visualization

Abstract

The paper presents an original approach for automated target recognition (ATR) in the synthetic aperture radar (SAR) imagery using the neural network classifier called Concurrent Self-Organizing Maps (CSOM), previously introduced by first author of the present paper. The ATR algorithm has the following stages: (a) image preprocessing (median filtering, histogram equalization, binarization); (b) feature selection using Gabor Filtering (GF); (c) neural classification with CSOM, representing a winner-takes-all collection of neural network modules. The algorithm has been applied for the recognition of three classes of military ground vehicles represented by the set of 2759 images of the MSTAR public release database. The experimental results obtained using CSOM has led to the best total success rate of 95.31%.