Share Email Print
cover

Proceedings Paper

Semi-supervised learning of heterogeneous data in remote sensing imagery
Author(s): J. Benedetto; W. Czaja; J. Dobrosotskaya; T. Doster; K. Duke; D. Gillis
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

We analyze Schroedinger Eigenmaps - a new semi-supervised manifold learning and recovery technique - for applications in hyperspectral imagery. This method is based on an implementation of graph Schroedinger operators with appropriately constructed potentials as carriers of expert/labeled information. In this paper, we analyze the features of Schroedinger Eigenmaps through analysis of the potential locations and their imapct on the classication. The imaging modalities which we shall incorporate in our analysis include multispectral and hyperspectral imagery. For the purpose of constructing ecient methods for building the potentials we refer to expert ground-truth data, as well as to using automated clustering techniques. We also investigate the role of dierent sources of the barrier potential locations, and the role they play in the separation of classes.

Paper Details

Date Published: 10 May 2012
PDF: 12 pages
Proc. SPIE 8401, Independent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering X, 840104 (10 May 2012); doi: 10.1117/12.919259
Show Author Affiliations
J. Benedetto, Univ. of Maryland, College Park (United States)
W. Czaja, Univ. of Maryland, College Park (United States)
J. Dobrosotskaya, Univ. of Maryland, College Park (United States)
T. Doster, Univ. of Maryland, College Park (United States)
K. Duke, Univ. of Maryland, College Park (United States)
D. Gillis, U.S. Naval Research Lab. (United States)


Published in SPIE Proceedings Vol. 8401:
Independent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering X
Harold Szu, Editor(s)

© SPIE. Terms of Use
Back to Top