Shape and data driven texture segmentation using local binary patterns

We prop ose a shape and data driven texture segmentation method using loca l binary patterns (LBP) and active contours. In particular, we pass textured images through a new LBP-based filter, which produces non-textured images. In this “filtered ” doma in each textured region of the original imag e exhibits a characteristic intensity distribution. In this domain we pose the segmentation problem as an optimization problem in a Bayesian framework. The cost functional contains a data-driven term, as well as a term that b ring s in information about the shapes of the objects to be segmented. We solve the optimization problem u sing level set-based active contours. Our experimental results on synthetic and real textures demonstrate the effectiveness of our approach in segmenting challenging textures as well as its robustness to missing data and occlusions.