Scale-space texture description on SIFT-like textons

Visual texture is a powerful cue for the semantic description of scene structures that exhibit a high degree of similarity in their image intensity patterns. This paper describes a statistical approach to visual texture description that combines a highly discriminative local feature descriptor with a powerful global statistical descriptor. Based upon a SIFT-like feature descriptor densely estimated at multiple window sizes, a statistical descriptor, called the multi-fractal spectrum (MFS), extracts the power-law behavior of the local feature distributions over scale. Through this combination strong robustness to environmental changes including both geometric and photometric transformations is achieved. Furthermore, to increase the robustness to changes in scale, a multi-scale representation of the multi-fractal spectra under a wavelet tight frame system is derived. The proposed statistical approach is applicable to both static and dynamic textures. Experiments showed that the proposed approach outperforms existing static texture classification methods and is comparable to the top dynamic texture classification techniques.

► We present a texture descriptor combining powerful global and local measurements.
► The multi-fractal spectrum is defined on discretized orientation histograms.
► A wavelet approach using tight wavelet frames robustifies the descriptor.
► The method is applied to static and dynamic textures.