DocumentCode
1796898
Title
Lossy compression of hyperspectral images using online learning based sparse coding
Author
Ulku, Irem ; Toreyin, B. Ugur
Author_Institution
Dept. of Electr. & Electron. Eng., Cankaya Univ., Ankara, Turkey
fYear
2014
fDate
1-2 Nov. 2014
Firstpage
1
Lastpage
5
Abstract
A lossy hyperspectral image compression method is proposed using online learning based sparse coding. The least number of coefficients are obtained to represent hyperspectral images by applying the sparse coding algorithm which is based on a dicriminative online dictionary learning method. Results indicate that a pre-analysis of the number of non-zero dictionary elements may help in improving the overall compression quality.
Keywords
compressed sensing; data compression; hyperspectral imaging; image coding; dicriminative online dictionary learning method; lossy hyperspectral image compression method; sparse coding algorithm; Dictionaries; Encoding; Equations; Hyperspectral imaging; Image coding; Mathematical model; PSNR; Anomaly Detection; Hyperspectral Imagery; Online Learning; Sparse Coding;
fLanguage
English
Publisher
ieee
Conference_Titel
Computational Intelligence for Multimedia Understanding (IWCIM), 2014 International Workshop on
Conference_Location
Paris
Type
conf
DOI
10.1109/IWCIM.2014.7008809
Filename
7008809
Link To Document