Image segmentation by weight adaptation and oscillatory correlation

We propose a novel approach for image segmentation on the basis of a neural oscillator network. Unlike previous approaches, weight adaptation is introduced during segmentation for noise removal and feature preservation. Moreover, a logarithmic grouping rule is proposed to facilitate grouping of oscillators representing pixels with coherent properties. We show that our weight adaptation scheme is insensitive to termination times, and the resulting dynamic weights in a wide range of iterations lead to the same segmentation results. A computer algorithm derived from oscillatory dynamics is applied to synthetic and real images, and simulation results show that the algorithm yields favorable segmentation results.