A method for mixed states texture segmentation with simultaneous parameter estimation

Authors:
A. Mailing;B. Cernuschi-Frías
Affiliations:
Engineering Faculty of the University of Buenos Aires, Argentina and Argentinian Mathematics Institute of CONICET, Argentina;Engineering Faculty of the University of Buenos Aires, Argentina and Argentinian Mathematics Institute of CONICET, Argentina
Venue:
Pattern Recognition Letters
Year:
2011

Citing 8
Cited 1

Unsupervised Learning of Multiple Motifs in Biopolymers Using Expectation Maximization

Machine Learning - Special issue on applications in molecular biology
A view of the EM algorithm that justifies incremental, sparse, and other variants

Learning in graphical models
Dynamic Textures

International Journal of Computer Vision
Dynamic Texture Segmentation

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
A New Method of Cluster-Based Topic Language Model for Genomic IR

AINAW '07 Proceedings of the 21st International Conference on Advanced Information Networking and Applications Workshops - Volume 01
On convergence properties of the em algorithm for gaussian mixtures

Neural Computation
Mixed-state causal modeling for statistical KL-based motion texture tracking

Pattern Recognition Letters
Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images

IEEE Transactions on Pattern Analysis and Machine Intelligence

Segmenting focused objects based on the Amplitude Decomposition Model

Pattern Recognition Letters

Quantified Score

Hi-index	0.10

Visualization

Abstract

In this work a method for mixed-state model motion texture segmentation and parameter estimation is presented. We use the Expectation Maximization algorithm for mixture parameter estimation, introducing the Gibbs distribution for moving points, excluding zero discrete component associated with no motion regions. We use then the a posteriori probabilities to generate an alternative field to segment the textures according to its statistical parameters.