Fast-Match: Fast Affine Template Matching

Simon Korman, Daniel Reichman, Gilad Tsur, Shai Avidan

Research output: Contribution to journalArticlepeer-review

Abstract

Fast-Match is a fast algorithm for approximate template matching under 2D affine transformations that minimizes the Sum-of-Absolute-Differences (SAD) error measure. There is a huge number of transformations to consider but we prove that they can be sampled using a density that depends on the smoothness of the image. For each potential transformation, we approximate the SAD error using a sublinear algorithm that randomly examines only a small number of pixels. We further accelerate the algorithm using a branch-and-bound-like scheme. As images are known to be piecewise smooth, the result is a practical affine template matching algorithm with approximation guarantees, that takes a few seconds to run on a standard machine. We perform several experiments on three different datasets, and report very good results.

Original languageAmerican English
Pages (from-to)111-125
Number of pages15
JournalInternational Journal of Computer Vision
Volume121
Issue number1
DOIs
StatePublished - 1 Jan 2017

Keywords

  • Image matching
  • Pattern matching
  • Sublinear algorithms
  • Template matching

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Fast-Match: Fast Affine Template Matching'. Together they form a unique fingerprint.

Cite this