Multispectral LANDSAT images segmentation using neural networks and multi-experts approach

Author

Solaiman, B. ; Mouchot, M.C. ; Koffi, R.K.

Author_Institution

Ecole Nat. Superieure des Telecommun. de Bretagne, Brest, France

Volume

4

fYear

1994

fDate

8-12 Aug 1994

Firstpage

2109

Abstract

The application of a combined segmentation method using the Canny-Deriche filter and a multi layer perceptron neural network is considered. The segmentation of five LANDSAT spectral bands is conducted. Obtained segmented images are combined using a multi experts approach in order to improve the segmentation quality and to preserve the land cover regions

Keywords

geophysical signal processing; geophysical techniques; image classification; image colour analysis; image segmentation; multilayer perceptrons; optical information processing; remote sensing; Canny-Deriche filter; LANDSAT; geophysical measurement technique; image classification; image processing; image segmentation; land cover; land surface terrain mapping; multi-experts approach; multilayer perceptron; multispectral method; neural net; neural network; optical imaging IR imaging infrared; Artificial neural networks; Filters; Hysteresis; Image segmentation; Image texture analysis; Neural networks; Remote sensing; Satellites; Smoothing methods; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium, 1994. IGARSS '94. Surface and Atmospheric Remote Sensing: Technologies, Data Analysis and Interpretation., International

Conference_Location

Pasadena, CA

Print_ISBN

0-7803-1497-2

Type

conf

DOI

10.1109/IGARSS.1994.399666

Filename

399666