Nonlinear Gaussian filtering approach for object segmentation

Gaussian filter kernels can be used to smooth textures for image segmentati on. In so-called anisotropic diffusion techniques, the smoothing process is adapted according to the edge direction to preserve the edges. However, th e segment borders obtained with this approach do not necessarily coincide w ith physical object contours, especially in the case of textured objects. A novel segmentation technique involving weighted Gaussian filtering is intr oduced. The extraction of true object masks is performed by smoothing edges due to texture and preserving true object borders. In this process, additi onal features such as disparity or motion are taken into account. The metho d presented has been successfully applied in the context of object segmenta tion to natural scenes and object-based disparity estimation for stereoscop ic applications.