Shape recognition is fundamental and important in spatial data-mining and in spatial cognition. In small-scale map generalization, the simplification of buildings takes an important place. In this paper, a pattern matching algorithm based on Fourier transform was used in order to select from a set of templates, a building outline that best characterizes a more detailed form. This research has explored the feasibility of automating simplification of buildings using shape recognition. Through the experiment of template matching, the initial set of results was very encouraging, and basically cons...