Non-parametric information geometry and multi-scale models of texture

We develop a novel algorithmic representation of textures using the statistics of multiple spectral components of images. Histograms of filter responses are viewed as elements of a non-parametric statistical manifold, and local texture patterns are compared using a geodesic metric derived from Riemannian information geometry. Several region-based image segmentation experiments are carried out to test the proposed representation and metric. This representation of textures is applied to the development of a spectral cartoon model of images.