Recognition of Dynamic Texture Patterns Using CHLAC Features

In this paper, we propose a statistical scheme for recognizing three-dimensional textures shown in motion images, which we call dynamic textures. The texture characteristics emerges in the distinct movement in the motion images, and the dynamic cues would be useful especially for recognizing ambiguous texture patterns in noisy images. We apply cubic higher-order auto-correlation (CHLAC) to extract features both of the textures and their movements, and then simply multiple regression analysis (MRA) to evaluate (recognize) the texture. In the experiment for estimating quality of beef meat by using ultrasound motion images, the proposed method exhibits the favorable performances which are close to ground truth given by the experts.