Feature selection for texture recognition based on image synthesis

An efficient method for selection of features suitable for classification of textured images is presented. The spatial interaction of gray levels in a local neighborhood N is modeled by stochastic random field models. The estimates of the model parameters are taken as textural features denoted by f
N
. Selection of an N that would yield powerful features is done through visual examination of images synthesized using f
N
. Experimental studies involving nine different types of natural textures yield 97-percent classification accuracy.