Abstract: Limitations of conventional Hausdorff distance (HD) measures are analyzed. Then focusing on these limitations, the robust HD measure is proposed that takes into account the image factors such as position and total number of edge points, spurious edge segments containing a very limited number of edge points, outlier points, and edge occlusions. As a result, the limitations of conventional measures are overcome. Experiment results for both synthetic and real images show that the proposed HD measure is more efficient than the conventional HD measures.