SAR automatic target recognition based on a visual cortical system

Author

Jia Cheng Ni ; Yue Lei Xu

Author_Institution

Inst. of Aeronaut. & Astronaut. Eng., Air Force Eng. Univ., Xian, China

Volume

2

fYear

2013

fDate

16-18 Dec. 2013

Firstpage

778

Lastpage

782

Abstract

Human Vision system is the most complex and accurate system. In order to extract better features about Synthetic Aperture Radar (SAR) targets, a SAR automatic target recognition (ATR) algorithm based on human visual cortical system is proposed. This algorithm contains three stages: (1) Image preprocessing (we use a Kuan filter to do the enhancement and an adaptive Intersecting Cortical Model (ICM) to do the segmentation) (2) Feature extraction using a sparse autoencoder. (3) Classification using a softmax regression classifier. Experiment result of MSTAR public data shows a better performance of recognition.

Keywords

feature extraction; filtering theory; image classification; image segmentation; synthetic aperture radar; Image preprocessing; Kuan filter; MSTAR public data; SAR automatic target recognition algorithm; feature extraction; human visual cortical system; intersecting cortical model; softmax regression classifier; sparse autoencoder; synthetic aperture radar; Classification algorithms; Computer architecture; Feature extraction; Synthetic aperture radar; Target recognition; Training; Visualization; ICM; Object Recognition; SAR; Sparse Autoencoder; Visual Cortex;

fLanguage

English

Publisher

ieee

Conference_Titel

Image and Signal Processing (CISP), 2013 6th International Congress on

Conference_Location

Hangzhou

Print_ISBN

978-1-4799-2763-0

Type

conf

DOI

10.1109/CISP.2013.6745270

Filename

6745270