Texture conditional local variance model in fuzzy-based unsupervised segmentation approach

Author

Velloso, Maria Luiza F ; De Souza, Flávio Joaquim ; De Almeida, Nival N.

Author_Institution

Dept. of Electron. Eng., Rio de Janeiro State Univ., Brazil

Volume

2

fYear

2004

fDate

20-24 Sept. 2004

Firstpage

1414

Abstract

This paper presents a fuzzy-based unsupervised segmentation of textured images driven by integrated spectral and spatial features. Spectral information can be obtained directly from pixel values in different frequency-band images, while spatial information can be extracted by mean of texture analysis. A new model, based on a multiplicative autoregressive random field model, was used as texture.

Keywords

autoregressive processes; feature extraction; fuzzy systems; image classification; image segmentation; image texture; remote sensing; unsupervised learning; MARC model; Multiplicative Autoregressive Random Field model; frequency-band image; fuzzy-based unsupervised segmentation; image classification; image texture analysis; spectral-spatial feature integration; texture conditional local variance model; Data mining; Feature extraction; Image analysis; Image classification; Image processing; Image segmentation; Image texture analysis; Information analysis; Remote sensing; Spatial resolution;

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.2004.1368684

Filename

1368684