A model validation approach to texture recognition

A new approach to texture recognition problem is proposed. The approach is based on model validation techniques from robust control theory. The solution to this problem includes modeling textures by uncertain dynamical systems. The modeling method is efficient in terms of computational and memory requirements, and the periodic nature of the result guarantees an infinite synthesizing of texture. The main aspects of the method include system identification and order reduction of marginally stable uncertain discrete-time systems. To demonstrate the results, both static-image textures and video textures are considered.