Efficient Segmentation of Piecewise Smooth Images

摘要

We propose a fast and robust segmentation model for piece-wise smooth images. Rather than modeling each region with global statistics, we introduce local statistics in an energy formulation. The shape gradient of this new functional gives a contour evolution controlled by local averaging of image intensities inside and outside the contour. To avoid the computational burden of a direct estimation, we express these terms as the result of convolutions. This makes an efficient implementation via recursive filters possible, and gives a complexity of the same order as methods based on global statistics. This approach leads to results similar to the general Mumford-Shah model but in a faster way, without solving a Poisson partial differential equation at each iteration. We apply it to synthetic and real data, and compare the results with the piecewise smooth and piecewise constant Mumford-Shah models.