Naslov
Wavelet transforms with application in signal denoising

Autori
Tomić, Mladen

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Annals of DAAAM & Proceedings for 2008 / - Beč : DAAAM International Vienna, 2008

ISBN
978-3-901509-68-1

Skup
19th DAAAM International Symposium "Intelligent Manufacturing & Automation"

Mjesto i datum
Trnava, Slovačka, 22.10.2008. - 25.10.2008

Vrsta sudjelovanja
Ostalo

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
wavelets; denoising; shrinkage; thresholding

Sažetak
This paper is focused on application of the wavelet transforms in signal denoising. Wavelet transforms have ability to localize the signal properties in both the frequency and the time. Signal decomposition results in packing the main signal properties in a small number of large wavelet coefficients and constraining noise to small coefficients. To remove noise from the signal, wavelet shrinkage technique is used – thresholding is applied to wavelet coefficients at each scale. This way, only larger coefficients are retained, while the coefficients representing noise are eliminated before the reconstruction. An example of signal decomposition and denoising is provided, in which these effects can be easily observed.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA