Synthesising Textures Using Variable Neighbourhood Searching

Texture synthesis aims to define and reproduce discriminating image features. These features are used to associate with and differentiate between two textures. Often texture is composed of a pattern with an element of randomness in each feature’s appearance, position and orientation. The goal is to imitate the sample texture in such a way that sample and synthesised texture are perceived to be generated by the same source. One of the recent texture synthesis methods selects an output pixel by searching with its already generated neighbourhood for a corresponding match in the sample image. The neighbourhood size is fixed and blurring of texture features often results. Our method attempts to avoid this problem by enabling a dynamic, accelerated neighbourhood search. The window size varies with each output pixel and is determined by the current neighbourhood intensity configuration.