Share Email Print
cover

Proceedings Paper

Remote sensing images segmentation by Deriche's filter and neural network
Author(s): Raphael K. Koffi; Basel Solaiman; Marie-Catherine Mouchot
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

An image segmentation method for remote sensing data using hybride techniques is proposed. Edge detection approach for segmentation is considered in our study. Our aim is to integrate segmentation results in further processing namely classification. Images of the land from satellite are often corrupted by noise. On one hand, optimal edge detectors insure good noise immunity. On the other hand, the multi-layer perceptron (MLP) neural network has been found to be suited for classification. So we propose to combine these two techniques to improve segmentation process. Satellites for remote sensing provide several images for the same area, coded differently according to spectral bands. In order to bear in mind spectral and spatial information, neighborhood relation of pixels and different bands are taken into consideration during the classification realized by the neural network. Samples which constituate the training set for the MLP are selected from the third, fourth and fifth band and represent edge and non-edge patterns. Each sample vector is composed of the value of a current pixel in the local maxima image (enhancement image obtained by Deriche's filter) and its 8 nearest neighbors. The proposed method provides satisfactory results for our application and compared to other similar methods.

Paper Details

Date Published: 30 December 1994
PDF: 9 pages
Proc. SPIE 2315, Image and Signal Processing for Remote Sensing, (30 December 1994); doi: 10.1117/12.196761
Show Author Affiliations
Raphael K. Koffi, Ecole Nationale Superieure des Telecommunications (France)
Basel Solaiman, Ecole Nationale Superieure des Telecommunications (France)
Marie-Catherine Mouchot, Ecole Nationale Superieure des Telecommunications (France)


Published in SPIE Proceedings Vol. 2315:
Image and Signal Processing for Remote Sensing
Jacky Desachy, Editor(s)

© SPIE. Terms of Use
Back to Top