An information fusion method for multispectral image classification postprocessing

Author

De Meneses, Jorge López ; Solaiman, Basel ; Koffi, Raphaël ; Mouchot, Marie-Catherine

Author_Institution

Dept. d´´Image et Traitement de l´´Inf., Ecole Nat. Superieure des Telecommun. de Bretagne, Brest, France

Volume

1

fYear

34881

fDate

10-14 Jul1995

Firstpage

99

Abstract

A post-processing technique is presented. Its goal is to produce classification images with sharp interclass boundaries and homogeneous regions. The chosen approach is the fusion of different available sources of information on the image to be analyzed. The method has been successfully applied to LANDSAT images, classified with neural networks, yielding to very encouraging results

Keywords

edge detection; geophysical signal processing; image classification; image segmentation; neural nets; remote sensing; sensor fusion; LANDSAT images; homogeneous regions; information fusion method; interclass boundaries; multispectral image classification postprocessing; neural networks; Change detection algorithms; Image edge detection; Information analysis; Information resources; Joining processes; Multispectral imaging; Neural networks; Pixel; Remote sensing; Voting;

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.1995.519659

Filename

519659