Aiming at the issue of point cloud or mesh model, which can be approximated using cubic B-spline surfaces, an algorithm of optimizing the knot vector based on Gaussian Mixture Model(GMM) is proposed in this paper. In addition, the control points of sub-corner points are searched by the Particle Swarm Optimization (PSO) in the process of stitching two B-spline surfaces with different knot vectors. Compared with conventional B-spline surface skinning, the proposed algorithms have two advantages. First, the global optimum is easy to be found by statistically learning and sampling in accordance with the probability distribution of the best individuals. Second, the stitching surface obtained is much smoother and the precise of approximate surface is also higher. The effectiveness of the proposed algorithm have been demonstrated according to experimental examples.