In this paper, an algorithm of image segmentation using region-based MRF combined with boundary information is
proposed. Firstly we obtain the initial over segmentation regions by Meanshift (MS) algorithm and the regions that
include seed points are set to seed regions. Then, starting from the seed regions, the finally result is detected under the
framework of MRF, where an image model is built for the potential function of the regional MRF image segmentation
and combined with edge strength to define a suitable MRF potential function, which is based on the similarity criterion
of the value of the edge. The experimental results indicate that the algorithm can promote the adaptive capacity of the
MRF model and reserve more details as well as region homogeneous.