Title :
Image enhancement via blind decomposition techniques
Author :
Polat, Özgür Murat ; Özkazanç, Yakup S.
Author_Institution :
TUBITAK- BILGEM, UEKAE, İltaren, Turkey
Abstract :
Unsupervised learning and blind signal decomposition methods are used for recovering unknown source signals from their linear mixtures using the observed data only. In these methods, a new representation of the data can reveal some hidden information inherent in the data. In this study, principal component analysis, independent component analysis and non-negative matrix factorization methodologies are applied on a single image for extracting information and image enhancement.
Keywords :
blind source separation; data structures; image enhancement; principal component analysis; unsupervised learning; blind decomposition technique; blind signal decomposition method; data representation; image enhancement; independent component analysis; information extraction; nonnegative matrix factorization methodology; principal component analysis; unknown source signal; unsupervised learning; Algorithm design and analysis; Conferences; Independent component analysis; Matrix decomposition; Principal component analysis; Signal processing; Signal processing algorithms;
Conference_Titel :
Signal Processing and Communications Applications (SIU), 2011 IEEE 19th Conference on
Conference_Location :
Antalya
Print_ISBN :
978-1-4577-0462-8
Electronic_ISBN :
978-1-4577-0461-1
DOI :
10.1109/SIU.2011.5929843
