The Hausdroff distance

a measure defined between two point sets

has been used to search for objects in images for its robustness and reliability. In this paper

a highly efficient approach

which uses the Hausdorff distance to locate an object that has undergone an affine transformation

is presented. Prior to our study

the most efficient methods for solving such a problem are two of Rucklidge' s methods:“without zoning" and“4×4 zoning". The proposed approach shares some similarities with Rucklidge' s methods but is mainly based on the“smallest square box distance transform" introduced in this paper. The idea of“smallest square box distance transform" is described in detail in this paper along with its implementation. By replacing the“box distance transform" of Rucklidge' s methods with our“smallest square box distance transform" in the search process

a much higher search speed can be achieved while maintaining the search success rate and target location accuracy. In all

two experiments are given in this paper. One experiment is to test the proposed approach on edge images and the other experiment is based on feature point images. It can be seen from the experimental results of both experiments that the proposed approach apparently outperforms Rucklidge's fast methods.