Segmentation of textured images using a multiresolution Gaussian autoregressive model

Abstract

We present a new algorithm for segmentation of textured images using a multiresolution Bayesian approach. The new algorithm uses a multiresolution Gaussian autoregressive (MGAR) model for the pyramid representation of the observed image, and assumes a multiscale Markov random field model for the class label pyramid. The models used in this paper incorporate correlations between different levels of both the observed image pyramid and the class label pyramid. The criterion used for segmentation is the minimization of the expected value of the number of misclassified nodes in the multiresolution lattice. The estimate which satisfies this criterion is referred to as the "multiresolution maximization of the posterior marginals" (MMPM) estimate, and is a natural extension of the single-resolution "maximization of the posterior marginals" (MPM) estimate. Previous multiresolution segmentation techniques have been based on the maximum a posterior (MAP) estimation criterion, which has been shown to be less appropriate for segmentation than the MPM criterion. It is assumed that the number of distinct textures in the observed image is known. The parameters of the MGAR model-the means, prediction coefficients, and prediction error variances of the different textures-are unknown. A modified version of the expectation-maximization (EM) algorithm is used to estimate these parameters. The parameters of the Gibbs distribution for the label pyramid are assumed to be known. Experimental results demonstrating the performance of the algorithm are presented.

Snake based unsupervised texture segmentation using Gaussian Markov Random Field Models

“…The algorithm may fall into local minima for some initial contours. We compare our algorithm with a multi-resolution Gaussian Markov Random Field (GMRF) with a second order neighborhood (autonormal model)[2][3] [4]. A simulated annealing algorithm is employed to maximize a posterior (MAP) probability [8].…”

Multiscale Segmentation Techniques for Textile Images

“…A double-stochastic model is proposed in [13] for multiresolution textured-image segmentation where the observed image is represented as a multiresolution Gaussian autoregressive (MGAR) model and class labels are assumed to be dependent on both the same scale and the adjacent finer and coarser scales as a 3-D MRF. The optimization criterion used for segmentation is the minimization of the expected value of the number of misclassified nodes in a multiresolution lattice.…”

“…Multiscale image segmentation approaches [1,[3][4][5][6][7][8][9][10][11][12][13][14] have been proven efficient to integrate both image features and contextual information to classify a region in an image differently from its surroundings if there is sufficient statistical evidence to justify a distinct region regardless of size, and refine the segmentation results recursively between different scales. The number of important contributions in this area is so great that just listing all of them would more than exhaust the page budget of this chapter (for example, the bibliography in [4] is 8 pages in a t w o -c o l u m n f o r m a t ) .…”

MRF-MBNN: A Novel Neural Network Architecture for Image Processing

“…To estimate the correlation coefficients θ, we adopt the modified version of the EM algorithm [11], which is an iterative procedure for approximating maximumlikelihood estimates. At each iteration, two steps are performed: the expectation step and the maximization step.…”