Robust Hausdorff distance fast matching algorithm using pyramidal structures

Robust Hausdorff Distance (HD) fast matching algorithm was implemented using the pyramidal structures that consist of an edge pyramidal and a distance transform pyramidal structure. To overcome the limits of directly simple sampling and lack of basis of theory, a new construction of edge pyramidal structure was proposed based on sampling strategy. An improved automatic threshold method was presented to select candidate positions at each level. Very promising experimental results using synthetic image and real images indicate that the proposed HD algorithm yields matching results similar to those achieved by the conventional HD algorithm with greatly reduced computational complexity with strong robustness.