Classification of rotated and scaled textured images using Gaussian Markov random field models

Rotation-invariant texture classification using feature distributions

“…Mao and Jain proposed a multivariate rotation-invariant simultaneous autoregressive model (RISAR) that is based on the CSAR model, and extended it to a multiresolution SAR model MR-RISAR) (5) . A method for classification of rotated and scaled textures using Gaussian Markov random field models was introduced by Cohen et al (6) . Approaches based on Gabor filtering have been proposed by, among others, Leung and Peterson (7) , Porat and Zeevi (8) , and Haley and Manjunath (9) .…”

Brief review of invariant texture analysis methods

“…Later, many model-based methods (including Gaussian Markov random ÿelds [18], Gibbs random ÿelds [47], and Wold model [22,23]) are introduced to model texture. In these methods, a texture image is modeled as a probability model or as a linear combination of a set of basis functions.…”

“…Cohen et al [18] model texture as Gaussian Markov random ÿelds and use the maximum likelihood to estimate coe cients and rotation angles. The problem of this method is that the likelihood function is highly nonlinear and local maxima may exist.…”

Rotation invariant texture descriptors based on Gaussian Markov random fields for classification

“…Texture analysis has been extensively studied in recent years and a large number of texture feature extraction techniques have been developed (Cohen et al, 1991;Nixon and Aguado, 2008;Varma and Zisserman, 2009;Zhao et al, 2012;Chen et al, 2010;Liu and Fieguth, 2012;Lei et al, 2014;Qi et al, 2012;Hinton and Salakhutdinov, 2006;Cimpoi et al, 2014;Simonyan et al, 2014). These methods can be roughly grouped into four main categories, namely statistical, structural, spectral and model based feature extraction methods (Xie and Mirmehdi, 2008).…”