Editing Template matching (section)

==Template-based approach==
[[File:Template Matching.png|thumb|Template matching with rotated templates]]
For templates without strong [[Feature (computer vision)|features]], or for when the bulk of a template image constitutes the matching image as a whole, a template-based approach may be effective. Since template-based matching may require sampling of a large number of data points, it is often desirable to reduce the number of sampling points by reducing the resolution of search and template images by the same factor before performing the operation on the resultant downsized images. This [[Data pre-processing|pre-processing]] method creates a multi-scale, or [[Pyramid (image processing)|pyramid]], representation of images, providing a reduced search window of data points within a search image so that the template does not have to be compared with every viable data point. Pyramid representations are a method of [[dimensionality reduction]], a common aim of machine learning on data sets that suffer the [[Curse of dimensionality#Data mining|curse of dimensionality]].