Paper Info
Title
A MULTIVARIATE GAUSSIAN MIXTURE MODEL OF LINEAR PREDICTION ERROR FOR COLOUR TEXTURE SEGMENTATION
Abstract
This paper presents an algorithm for parametric supervised colour texture segmentation using a novel image observa- tion model. The proposed segmentation algorithm consists of two phases: In the first phase, we estimate an initial class label field of the image based on a 2D multichannel complex linear prediction model. Information of both luminance and chrominance spatial variation feature cues are used to charac- terize colour textures. Complex multichannel version of 2D Quarter Plane Autoregressive model is used to model these spatial variations of colour texture images in CIE L*a*b* colour space. Overall colour distribution of the image is es- timated from the multichannel prediction error sequence of this Autoregressive model. Another significant contribution of this paper is the modelling of this multichannel error se- quence using Multivariate Gaussian Mixture Model instead of a single Gaussian probability. Gaussian parameters are calculated through Expectation Maximization on a training dataset. In second phase of the algorithm, initial class label field obtained through the first stage is spatially regularized by ICM algorithm to have the final segmented image. Visual and quantitative results for different number of components of Multivariate Gaussian Mixture Model are presented and discussed.
Year
DOI
Venue
2009
10.5281/zenodo.41641
European Signal Processing Conference
Field
DocType
ISBN
Autoregressive model,Pattern recognition,Expectation–maximization algorithm,Image segmentation,Linear prediction,Gaussian,Parametric statistics,Multivariate normal distribution,Artificial intelligence,Mathematics,Mixture model
Conference
978-161-7388-76-7
Citations 
PageRank 
References 
2
0.39
9
Authors
5
Name
Order
Citations
PageRank
Imtnan-Ul-Haque Qazi1362.68
Fatima Ghazi220.39
Olivier Alata311819.81
Jean-Christophe Burie427139.04
Christine Fernandez-Maloigne517035.22