We attack the problem of recognizing real, planar objects from two-dimensional, intensity images taken from arbitrary viewpoints using genetic algorithms. More specifically, we use genetic algorithms to search for a geometric mapping that brings subsets of points comprising the model and subsets of points comprising the scene into alignment. The genetic algorithm searches the image space and we compare different encodings and operators on a set of three increasingly complex scenes. Our preliminary results are promising with exact and near exact matches being found reliably and quickly.