OrsaHomography : automatic homographic registration of images

This software was developed (or is under development) within the higher education and research community. Its stability can vary (see fields below) and its working state is not guaranteed.
Higher Edu - Research dev card
  • Creation or important update: 22/09/13
  • Minor correction: 22/09/13
  • Index card author: Pascal Monasse (LIGM)
  • Theme leader: Teresa Gomez-Diaz (LIGM)
General software features

This software registers two images by homography. This registration is meaningful in the two following situations:

  • no motion of optical center (only rotation and focal change), or
  • the observed scene is planar (painting, poster, aerial photo from high altitude...)

The software detects SIFT matching candidate points, then it sorts correct and outlier correspondences thanks to a variant of the robust estimation algorithm RANSAC. This variant uses the a contrario framework to estimate automatically the discrimination threshold.

As output, the user gets a list of matching interest points, the homography matrix, registered images, and a panorama built from the registered images by transparency.

Context in which the software is used

This software illustrates the algorithm ORSA, also known as AC-RANSAC, applied to the case of homography estimation.

Publications related to software

Automatic Homographic Registration of a Pair of Images, with A Contrario Elimination of Outliers
Lionel Moisan, Pierre Moulon, Pascal Monasse
Image Processing On Line (IPOL), 2012.