DocumentCode :
3247036
Title :
Non-homogeneous hidden Markov chain models for wavelet-based hyperspectral image processing
Author :
Duarte, Marco F. ; Parente, Mario
Author_Institution :
Dept. of Electr. & Comput. Eng., Univ. of Massachusetts, Amherst, MA, USA
fYear :
2013
fDate :
2-4 Oct. 2013
Firstpage :
154
Lastpage :
159
Abstract :
We consider the use of non-homogeneous Markov chain (NHMC) models for wavelet transformations of hyperspectral signatures to generate features for signal processing purposes. Inspired by the use of hidden Markov trees for natural images, the NHMC model enables the characterization of absorption bands and other structural features of mineral spectra that are used by experts in tasks like classification and unmixing, primarily in an ad-hoc fashion. We show that NHMC models can successfully identify and capture the information in a spectral signature dataset that can be exploited by standard classification algorithms to identify and differentiate spectral families. We also identify several metrics that can help determine whether each spectral band is informative to classification in a multiscale fashion.
Keywords :
hidden Markov models; hyperspectral imaging; image classification; natural scenes; trees (mathematics); wavelet transforms; NHMC models; absorption bands; hidden Markov trees; hyperspectral signatures; mineral spectra; multiscale fashion; natural images; nonhomogeneous hidden Markov chain models; signal processing purpose; spectral family; spectral signature dataset; standard classification algorithms; structural features; wavelet transformations; wavelet-based hyperspectral image processing; Absorption; Hidden Markov models; Hyperspectral imaging; Measurement; Minerals; Wavelet transforms;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Communication, Control, and Computing (Allerton), 2013 51st Annual Allerton Conference on
Conference_Location :
Monticello, IL
Print_ISBN :
978-1-4799-3409-6
Type :
conf
DOI :
10.1109/Allerton.2013.6736518
Filename :
6736518
Link To Document :
بازگشت