An information fusion method for multrispectral image classification post-processing

Jorge Lopez de Meneses (1) , Basel Solaiman (1) , Kouamé Raphaël Koffi (1) , Marie-Catherine Mouchot (1)

1 ITI - Département Image et Traitement Information

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.

Mots clés: Multispectral imaging; Remote sensing; Pixel; Smoothing methods; Image classification; Satellites

Domaines: Traitement du signal et de l'image [eess.SP]

Jorge Lopez de Meneses, Basel Solaiman, Kouamé Raphaël Koffi, Marie-Catherine Mouchot. An information fusion method for multrispectral image classification post-processing. IGARSS'95 : IEEE Geoscience And Remote Sensing Symposium, Jul 1995, Florence, Italy. pp.99 - 101, ⟨10.1109/IGARSS.1995.519659⟩. ⟨hal-02159898⟩