Automated texture recognition system based on 2D minimum variance spectral estimation

Author

Mathur, Abhinav ; Younan, Nicholas H. ; Bruce, Lori Mann

Author_Institution

Dept. of Electr. & Comput. Eng., Mississippi State Univ., MS, USA

Volume

2

fYear

2004

fDate

20-24 Sept. 2004

Firstpage

1061

Abstract

The primary feature of any image texture is the spatial frequency content. This paper proposed the use of a 2D minimum variance spectral estimation (MVSE) method for recognizing target multispectral image textures. The power spectral density of the target texture is estimated via MVSE. This estimate is then used as a feature to discriminate between target and nontarget textures. A remotely sensed multispectral image of a row crop agricultural field is analyzed and, the corresponding results are presented to illustrate the applicability of the proposed technique.

Keywords

crops; image classification; image texture; remote sensing by radar; synthetic aperture radar; 2D minimum variance spectral estimation; MVSE; automated texture recognition system; multispectral image texture; power spectral density; remotely sensed image; row crop agricultural field; spatial frequency content; target recognizing; target/nontarget texture discrimination; Autocorrelation; Crops; Filters; Frequency estimation; Image analysis; Image texture; Image texture analysis; Multispectral imaging; Narrowband; State estimation;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium, 2004. IGARSS '04. Proceedings. 2004 IEEE International

Print_ISBN

0-7803-8742-2

Type

conf

DOI

10.1109/IGARSS.2004.1368594

Filename

1368594