Abstract

This paper presents a variational method for supervised texture segmentation, which is based on ideas coming from the curve propagation theory. We assume that a preferable texture pattern is known (e.g. the pattern that we want to distinguish from the rest of the image). The textured feature space is generated by filtering the input and the preferable pattern image using Gabor filters, and analyzing their responses as multi-component conditional probability density functions. The texture segmentation is obtained by minimizing a Geodesic Active Contour Model objective function where the boundary-based information is expressed via discontinuities on the statistical space associated with the multi-modal textured feature space. This function is minimized using a gradient descent method where the obtained PDE is implemented using a level set approach, that handles naturally the topological changes. Finally, a fast method is used for the level set implementation. The performance of our method is demonstrated on a variety of synthetic and real textured images. 1

Citations