Jump to content

Talk:Template matching

Page contents not supported in other languages.
From Wikipedia, the free encyclopedia

"We then simply move the center (or the origin) of the template T(x t, y t) over each (x, y) point in the search image and calculate the sum of products between the coefficients in S(x, y) and T(xt, yt) over the whole area spanned by the template."

How is this different from cross-correlation? or what Wikipedia calls Phase correlation?

"Other methods which are similar include 'Stereo matching,' 'Image registration' and 'Scale-invariant feature transform.'"

Isn't this a form of image registration? Not a "similar method".

Issue: The section "Template-based matching and convolution" points to convolution in (the mathematical definition) but the elaborated example -algorithm and formulas- are not related to convolution at all! — Preceding unsigned comment added by Carlosayam (talkcontribs) 07:45, 1 August 2013 (UTC)[reply]

Template matching seems to be synonymous to block matching. If so, shouldn't the articles be merged? Otherwise the difference should be made clearer. Does anyone know whether there is a difference? — Preceding unsigned comment added by 89.13.27.200 (talk) 16:20, 25 June 2017 (UTC)[reply]