Model based rotation-invariant texture classification

Abstract

In this paper a model based texture classification procedure robust to sample rotation is presented. The texture is modeled as the output of a linear system driven by a binary image. This latter retains the morphological characteristics of the texture and it is specified by its spatial autocorrelation function (ACF). We show that features extracted from the ACF of the binary excitation suffice to represent the texture for classification purposes. Specifically, we employ a classical moment invariants based technique to classify the ACF and the resulting classification procedure is thus inherently rotation invariant. Experimental results show that this approach allows obtaining high correct rotation-invariant classification rates while reducing the size of the feature space and the computational burden.