A single input three output model based approach to color texture generation

An innovative unsupervised color texture, model based, synthesis method is presented. It aims to reproduce a color texture perceptually similar to a given prototype. To achieve this task, we reconstruct the texture on a stochastic base, matching the prototype's statistics up to the second order to the synthesized texture ones. The model employed allows to replace the multiple input multiple output filters, which have to be used in the general case, with more simple structures, leading to a dramatical computational complexity reduction without affecting the results quality.