Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Supervised Laplacian Eigenmaps for Hyperspectral Data

 
: Becker, Florian

:
Volltext urn:nbn:de:0011-n-5521953 (7.1 MByte PDF)
MD5 Fingerprint: 54cac9d30796ebf936070a9d0efdf8c9
Erstellt am: 19.7.2019


Beyerer, Jürgen (Ed.); Taphanel, Miro (Ed.); Taphanel, Miro (Ed.):
Proceedings of the 2018 Joint Workshop of Fraunhofer IOSB and Institute for Anthropomatics, Vision and Fusion Laboratory
Karlsruhe: KIT Scientific Publishing, 2019 (Karlsruher Schriften zur Anthropomatik 40)
ISBN: 978-3-7315-0936-3
ISBN: 3-7315-0936-9
DOI: 10.5445/KSP/1000094782
S.77-88
Fraunhofer Institute of Optronics, System Technologies and Image Exploitation and Institute for Anthropomatics, Vision and Fusion Laboratory (Joint Workshop) <2018, Triberg-Nussbach>
Englisch
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IOSB ()

Abstract
With Laplacian eigenmaps the low-dimensional manifold of high-dimensional
data points can be uncovered. This nonlinear dimensionality reduction technique is popular due to its well-understood theoretical foundation. This paper outlines a straightforward way to incorporate class label information into the standard (unsupervised) Laplacian eigenmaps formulation. With the example of hyperspectral data samples this supervised reformulation is shown to reinforce within-class clustering and increase between-class distances.

: http://publica.fraunhofer.de/dokumente/N-552195.html