Non-negative Matrix Factorization Features from Spectral Signatures of AVIRIS Images

Author

Kaarna, Arto

Author_Institution

Dept. of Inf. Technol., Lappeenranta Univ. of Technol., Lappeenranta

fYear

2006

fDate

July 31 2006-Aug. 4 2006

Firstpage

549

Lastpage

552

Abstract

In this study we use non-negative matrix factorization (NMF) in deriving feature vectors from a set of spectral signatures. The purpose is to demonstrate the differences between the NMF and PCA feature vectors. The experiments show that NMF feature vectors are providing local features in spectral domain compared to the holistic features of PCA.

Keywords

image classification; principal component analysis; vegetation; AVIRIS images; NMF feature vector; PCA feature vector; nonnegative matrix factorization; spectral signatures; Humans; Image reconstruction; Independent component analysis; Information technology; Noise reduction; Principal component analysis; Prototypes; Singular value decomposition; Sparse matrices; Vector quantization;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium, 2006. IGARSS 2006. IEEE International Conference on

Conference_Location

Denver, CO

Print_ISBN

0-7803-9510-7

Type

conf

DOI

10.1109/IGARSS.2006.145

Filename

4241292

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=2853079