Share Email Print

Proceedings Paper

Automatic segmentation of textures on a database of remote-sensing images and classification by neural network
Author(s): Philippe Durand; Luan Jaupi; Dariush Ghorbanzdeh
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Analysis and automatic segmentation of texture is always a delicate problem. Objectively, one can opt, quite naturally, for a statistical approach. Based on higher moments, these technics are very reliable and accurate but expensive experimentally. We propose in this paper, a well-proven approach for texture analysis in remote sensing, based on geostatistics. The labeling of different textures like ice, clouds, water and forest on a sample test image is learned by a neural network. The texture parameters are extracted from the shape of the autocorrelation function, calculated on the appropriate window sizes for the optimal characterization of textures. A mathematical model from fractal geometry is particularly well suited to characterize the cloud texture. It provides a very fine segmentation between the texture and the cloud from the ice. The geostatistical parameters are entered as a vector characterize by textures. A neural network and a robust multilayer are then asked to rank all the images in the database from a learning set correctly selected. In the design phase, several alternatives were considered and it turns out that a network with three layers is very suitable for the proposed classification. Therefore it contains a layer of input neurons, an intermediate layer and a layer of output. With the coming of the learning phase the results of the classifications are very good. This approach can bring precious geographic information system. such as the exploitation of the cloud texture (or disposal) if we want to focus on other thematic deforestation, changes in the ice ...

Paper Details

Date Published: 8 November 2012
PDF: 10 pages
Proc. SPIE 8537, Image and Signal Processing for Remote Sensing XVIII, 85370D (8 November 2012); doi: 10.1117/12.974340
Show Author Affiliations
Philippe Durand, Conservatoire National des Arts et Métiers (France)
Luan Jaupi, Conservatoire National des Arts et Métiers (France)
Dariush Ghorbanzdeh, Conservatoire National des Arts et Métiers (France)

Published in SPIE Proceedings Vol. 8537:
Image and Signal Processing for Remote Sensing XVIII
Lorenzo Bruzzone, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?