Hyperspectral feature selection for forest classification

International Geoscience and Remote Sensing Symposium (IGARSS)

Volumn 2, Issue , 2004, Pages 1471-1474

  Han, Tian ^b   Goodenough, David G ^a,b   Dyk, Andrew ^a   Chen, Hao ^a  

^a PACIFIC FORESTRY CENTRE   (Canada)

^b UNIVERSITY OF VICTORIA   (Canada)

Author keywords

Canonical transformation; Classification; Feature selection; Hyperspectral; feature extraction; Minimum noise fraction; Principal components analysis

Indexed keywords

CANONICAL TRANSFORMATION; FEATURE SELECTION; HYPERSPECTRAL IMAGERY; MINIMUM NOISE FRACTION (MNF);

DATABASE SYSTEMS; EIGENVALUES AND EIGENFUNCTIONS; FEATURE EXTRACTION; IMAGE SENSORS; PRINCIPAL COMPONENT ANALYSIS; SPURIOUS SIGNAL NOISE;

FORESTRY;

DATA BASES; FORESTS; IMAGE ANALYSIS; NOISE;

EID: 15944403980     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (3)

1. David A. Landgrebe, Signal Theory Methods in Multispectral Remote Sensing, John Wiley & Sons, 2003.
2. rd Edition, Springer, 1999.
3. C. I. Chang and Q. Du, Interference and Noise-Adjusted Principal Components Analysis, IEEE Transactions on Geoscience and Remote Sensing, Vol. 37, No. 5, Sept. 1999.