Semi-Supervised Based Hyperspectral Imagery Classification

Hyperspectral imagery classification is a challenging problem. Wherein, the high number of spectral channels and the high cost of true sample labeling greatly reduce the classification precision. In this paper, we proposed a semi-supervised method, which combine linear discriminant analysis and mani...

Full beskrivning

Sparad:
Bibliografiska uppgifter
Huvudupphovsmän: Zhijun Zheng, Yanbin Peng
Materialtyp: Artigo
Språk:Inglês
Publicerad: IFSA Publishing, S.L. 2013-09-01
Serie:Sensors & Transducers
Ämnen:
Hyperspectral imagery
Classification
Semi-supervised
Linear discriminant analysis
Manifold learning.
Länkar:http://www.sensorsportal.com/HTML/DIGEST/september_2013/P_1360.pdf
Taggar: Lägg till en tagg
Inga taggar, Lägg till första taggen!

Liknande verk