In point-based monomodal image registration, registration accuracy relies heavily on control point (CP) locations and correspondences. However, CP extraction and correspondence establishment are still difficult under complex deformations, such as elastic deformations. To solve this problem, we present a novel approach to optimizing CP locations and simultaneously establishing the proper correspondence between these points. An expectation-maximization-like model and a refinement mechanism are proposed to achieve CP optimization as well as correspondence establishment. Experimental results for artificial and real registration tasks show that the proposed approach is robust and has good convergence behavior.