Sciweavers

101 search results - page 6 / 21
» Methods for merging Gaussian mixture components
Sort
View
TIP
2002
179views more  TIP 2002»
13 years 7 months ago
Unsupervised image classification, segmentation, and enhancement using ICA mixture models
An unsupervised classification algorithm is derived by modeling observed data as a mixture of several mutually exclusive classes that are each described by linear combinations of i...
Te-Won Lee, Michael S. Lewicki
ADMI
2010
Springer
13 years 9 months ago
Probabilistic Modeling of Mobile Agents' Trajectories
Abstract. We present a method for learning characteristic motion patterns of mobile agents. The method works on two levels. On the first level, it uses the expectation-maximization...
Stepán Urban, Michal Jakob, Michal Pechouce...
ICIAP
2007
ACM
14 years 1 months ago
Rigid Image Registration based on Pixel Grouping
We propose a pixel similarity-based algorithm enabling accurate rigid registration between single and multimodal images. The method relies on the partitioning of a reference image...
Demetrios Gerogiannis, Christophoros Nikou, Aristi...
ISCAS
2005
IEEE
214views Hardware» more  ISCAS 2005»
14 years 1 months ago
Blind separation of statistically independent signals with mixed sub-Gaussian and super-Gaussian probability distributions
— In the context of Independent Component Analysis (ICA), we propose a simple method for online estimation of activation functions in order to blindly separate instantaneous mixt...
Muhammad Tufail, Masahide Abe, Masayuki Kawamata
ICASSP
2008
IEEE
14 years 2 months ago
Singer melody extraction in polyphonic signals using source separation methods
We propose a new approach for singer melody extraction, based on blind source separation techniques. The short time Fourier transform (STFT) of the singer signal is modelled by a ...
Jean-Louis Durrieu, Gaël Richard, Bertrand Da...