Texture segmentation using Gaussian-Markov random fields and neural oscillator networks

We propose an image segmentation method based on texture analysis. Our meth od is composed of two parts; The first part determines a novel set of textu re features derived from a Gaussian-Markov random fields (GMRF) model. Unli ke a GMRF-based approach, our method does not employ model parameters as fe atures or require the extraction of features for a fixed set of texture typ es a priori. The second part is a two-dimensional (2-D) array of locally ex citatory globally inhibitory oscillator networks (LEGION). After being filt ered for noise suppression, features are used to determine the local coupli ngs in the network,When LEGION runs, the oscillators corresponding to the s ame texture tend to synchronize, whereas different texture regions tend to correspond to distinct phases. In simulations, a large system of differenti al equations is solved for the first time using a recently proposed method for integrating relaxation oscillator networks. We provide results on real texture images to demonstrate the performance of our method.