DocumentCode :
1932992
Title :
Complex SAR image characterization using space variant spectral analysis
Author :
Popescu, Anca ; Gavat, Inge ; Datcu, Mihai
Author_Institution :
Telecommun. & Inf. Technol., Politeh. Univ. Bucharest, Bucharest
fYear :
2008
fDate :
26-30 May 2008
Firstpage :
1
Lastpage :
4
Abstract :
This paper proposes a new parameter based method of SAR image feature extraction and complex image information retrieval. The methodpsilas groundwork is the Fast Fourier Transform, each of the proposed parameters being built on a Fourier Transform basis. We suggest that by the use of several image bands formed of distinct spectral signatures of the original complex image, one can obtain a valid spectral characterization of the SAR image that can be afterwards subject to a clustering algorithm. The classification algorithm proposed in this paper is unsupervised K- means. The main advantages of the algorithm are the simplicity and robustness of the implementation.
Keywords :
fast Fourier transforms; feature extraction; image classification; image retrieval; information retrieval; radar computing; radar imaging; spectral analysis; synthetic aperture radar; unsupervised learning; classification algorithm; clustering algorithm; fast Fourier transform; image information retrieval; space variant spectral signature analysis; synthetic aperture radar image characterization; synthetic aperture radar image feature extraction; unsupervised learning algorithm; Aperture antennas; Azimuth; Bandwidth; Clustering algorithms; Fourier transforms; Image retrieval; Information retrieval; Radar antennas; Spectral analysis; Synthetic aperture radar; FFT; K-means clustering; multiband image;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Radar Conference, 2008. RADAR '08. IEEE
Conference_Location :
Rome
ISSN :
1097-5659
Print_ISBN :
978-1-4244-1538-0
Electronic_ISBN :
1097-5659
Type :
conf
DOI :
10.1109/RADAR.2008.4720990
Filename :
4720990
Link To Document :
بازگشت