An auto tuned noise resistant descriptor for dynamic texture recognition

Abstract

This paper presents a scheme for the representation and recognition of the dynamic texture in the noisy environment. Dynamic texture is the sequence of images of a moving scene that shows some form of temporal regularity. Though, the dynamic texture is the spatiotemporal extension of the conventional texture, its analysis requires additional attention, since the motion causes continuous changes in the geometry of these textures. Hence, to recognize the noisy dynamic texture, the noise should be estimated not only at the spatial level; it must also be estimated at the temporal level. To this end, an auto tuned noise resistance descriptor, based on the Local Binary Pattern approach, is proposed for the modeling and classification of the dynamic texture. Our approach based on the fact that, uniform local binary patterns are the fundamental units of image texture and occur more frequently in an image in comparison to non-uniform patterns. Noise affects these uniform local binary patterns and more likely fall into non-uniform codes. To counter this, we have extended conventional local binary pattern descriptor from a 2-value code to a 3-value code to include an additional state (called indecisive state) to represent the noise affected pixels. However, the estimation of the indecisive state is of the primary concern of this letter due to the inherently varying nature of the dynamic texture. The proposed technique devised a new scheme to estimate the noisy pixels in a dynamic texture. Eventually, the indecisive state is corrected back to non-noisy natural states using a mapping function so as to form a uniform LBP code. Experimental results on the UCLA and Dyntex++ databases demonstrate high classification efficiency of the proposed approach in the noisy environment.