Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

15

ICPR
2000
IEEE

favoriteEmaildiscussreport

101views computer vision» more ICPR 2000»

Unsupervised Selection and Estimation of Finite Mixture Models

14 years 5 months ago

Unsupervised Selection and Estimation of Finite Mixture Models

Download dataclustering.cse.msu.edu

We propose a new method for fitting mixture models that performs component selection and does not require external initialization. The novelty of our approach includes: a minimum message length (MML) type model selection criterion; the inclusion of the criterion into the expectation-maximization (EM) algorithm (which also increases its ability to escape from local maxima); an initialization strategy supported on the interpretation of EM as a self-annealing algorithm.

Anil K. Jain, Mário A. T. Figueiredo

Real-time Traffic

Computer Vision | External Initialization | ICPR 2000 | Initialization Strategy | Model Selection Criterion |

claim paper

Related Content

» Unsupervised Selection and Discriminative Estimation of Orthogonal Gaussian Mixture Models...

» Unsupervised Greedy Learning of Finite Mixture Models

» Unsupervised Learning of Finite Mixture Models

» Automated Model Selection AMS on Finite Mixtures A Theoretical Analysis

» Variational approximations in Bayesian model selection for finite mixture distributions

» An Unsupervised Gaussian Mixture Classification Mechanism Based on Statistical Learning An...

» Bayesian Feature and Model Selection for Gaussian Mixture Models

» Mixture Density Mercer Kernels A Method to Learn Kernels Directly from Data

» Manifold Constrained Finite Gaussian Mixtures

Post Info
More Details (n/a)

Added	09 Nov 2009
Updated	09 Nov 2009
Type	Conference
Year	2000
Where	ICPR
Authors	Anil K. Jain, Mário A. T. Figueiredo

Comments (0)