Finding correspondences between contour points in consecutive frames is crucial for the left ventricular motion analysis. In many medical applications, point correspondences can be determined by using distinctive anatomical features, called anatomical landmarks. However, in the case of cardiac images, these landmarks are scarce and insufficient for the registration. Several methods have been proposed using semi-landmarks, but this may lead to incorrect correspondences. This paper proposes and evaluates the performance of three point matching algorithm. Results show that the matching by resampling method leads to the best overall correspondences and compares favorably with the performance of a state of the art shape alignment algorithm [9].