Image classification based on beta distribution for SAR image

Author

Arai, Kohei ; Terayama, Yasunori ; Arata, Tsutoshi

Author_Institution

Dept. of Inf. Sci., Saga Univ., Japan

Volume

2

fYear

34881

fDate

10-14 Jul1995

Firstpage

1263

Abstract

A new method for SAR image classification is proposed. The method is based on maximum likelihood decision rule with texture features and takes into account the probability density function of texture features. The experimental results show the proposed method is superior to the existing maximum likelihood method with multivariate normal distribution. 2.28 to 5.16% of improvements are observed with real SAR image. Effects of local least square estimator, sigma and weighting filters for speckle noise reduction on classification performance are clarified. The results show that 7.1 to 12.04 % of improvements on the classification performance are observed

Keywords

feature extraction; geophysical signal processing; geophysical techniques; image classification; image texture; radar imaging; remote sensing by radar; synthetic aperture radar; SAR image; SAR imagery; beta distribution; feature extraction; geophysical measurement technique; image classification; image processing; image texture; land surface; local least square estimator; maximum likelihood decision rule; multivariate normal distribution; probability density function; radar remote sensing; sigma filter; speckle noise reduction; synthetic aperture radar; terrain mapping; weighting filter; Equations; Filters; Gaussian distribution; Image classification; Information science; Least squares approximation; Least squares methods; Maximum likelihood estimation; Noise reduction; Pixel; Probability density function; Speckle;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium, 1995. IGARSS '95. 'Quantitative Remote Sensing for Science and Applications', International

Conference_Location

Firenze

Print_ISBN

0-7803-2567-2

Type

conf

DOI

10.1109/IGARSS.1995.521720

Filename

521720