Editing Template matching (section)

== Speeding up the process ==

In the past, this type of spatial filtering was normally only used in dedicated hardware solutions because of the computational complexity of the operation,<ref>Gonzalez, R, Woods, R, Eddins, S "[https://web.archive.org/web/20190723164704/https://pdfs.semanticscholar.org/ff38/489bbc62d765c8621b32e121ec2814e4fb1f.pdf Digital Image Processing using Matlab]" Prentice Hall, 2004</ref> however we can lessen this complexity by filtering it in the frequency domain of the image, referred to as 'frequency domain filtering,' this is done through the use of the [[convolution theorem]].

Another way of speeding up the matching process is through the use of an image pyramid. This is a series of images, at different scales, which are formed by repeatedly filtering and subsampling the original image in order to generate a sequence of reduced resolution images.<ref>E. H. Adelson, C. H. Anderson, J. R. Bergen, P. J. Burt and J. M. Ogden, Pyramid methods in image processing http://web.mit.edu/persci/people/adelson/pub_pdfs/RCA84.pdf</ref> These lower resolution images can then be searched for the template (with a similarly reduced resolution), in order to yield possible start positions for searching at the larger scales. The larger images can then be searched in a small window around the start position to find the best template location.

Other methods can handle problems such as translation, scale, image rotation and even all affine transformations.<ref>Yuan, Po, M.S.E.E. "Translation, scale, rotation and threshold invariant pattern recognition system". The University of Texas at Dallas, 1993, 62 pages; AAT EP13780</ref><ref>H. Y. Kim and S. A. Araújo, "[https://www.researchgate.net/profile/Hae_Kim2/publication/221411551_Grayscale_Template-Matching_Invariant_to_Rotation_Scale_Translation_Brightness_and_Contrast/links/00463516819b8ca844000000/Grayscale-Template-Matching-Invariant-to-Rotation-Scale-Translation-Brightness-and-Contrast.pdf Grayscale Template-Matching Invariant to Rotation, Scale, Translation, Brightness and Contrast]," IEEE Pacific-Rim Symposium on Image and Video Technology, Lecture Notes in Computer Science, vol. 4872, pp. 100-113, 2007.</ref><ref>Korman S., Reichman D., Tsur G. and Avidan S., "[http://openaccess.thecvf.com/content_cvpr_2013/papers/Korman_FasT-Match_Fast_Affine_2013_CVPR_paper.pdf FAsT-Match: Fast Affine Template Matching]", CVPR2013.</ref>