Title :
Extraction and selection of robust features for classification of multispectral remote-sensing images
Author :
Bruzzone, Lorenzo ; Prieto, Diego Fernández ; Silvano, Giovanni
Author_Institution :
Dept. of Biophys. & Electron. Eng., Genoa Univ., Italy
Abstract :
In this paper, we present an approach to the extraction and selection of robust features for classification of multispectral remote-sensing images. In particular, several robust features are proposed that, given a specific land-cover class, aim to exhibit an invariant behavior versus variations in the acquisition conditions of the images considered. In addition, a technique is presented, which is able to adaptively select the most robust features for a given problem
Keywords :
feature extraction; geophysical signal processing; image classification; remote sensing; acquisition conditions; classification; extraction; invariant behavior; land-cover; multispectral remote-sensing images; robust features; selection; Absorption; Electronic mail; Feature extraction; Pixel; Reflectivity; Remote sensing; Robustness; Sensor phenomena and characterization; Shape measurement; Soil moisture;
Conference_Titel :
Geoscience and Remote Sensing Symposium, 1999. IGARSS '99 Proceedings. IEEE 1999 International
Conference_Location :
Hamburg
Print_ISBN :
0-7803-5207-6
DOI :
10.1109/IGARSS.1999.773420
