Siemens Aktiengesellschaft

Ecole Centrale De Paris

Benjamin Glocker

Nassir Navab

Nikos Paragios

Jochen Zeltner

Nikos Komodakis

Christian Wachinger

A method of combining a first image of a first region and a second image of a second region, having an overlapping region therebetween. The method including determining a superposed image as a weighted superposition of the first image and the second image in the overlap region, transforming the first image and the second image on the basis of a comparison of at least one of the first image and the second image with the determined superposed image; determining a further superposed image from the transformed first image and the transformed second image; and generating an overall image from the further superposed image when at least one convergence criterion is satisfied.

Method for combining images and magnetic resonance scanner

A method for registering digitized images using Markov Random Fields (MRFs) includes providing a source image f and a target image g, defining a deformation grid of control points, defining a coordinate transformation as where x is a point on the source image, p is a position vector of control point p, dis a displacement vector for each control point, uis a label for point p associated with displacement d, and &#x3b7;( ) is a weighting function for the displacement vector, defining an MRF energy functional to be minimized by T as wherein |G| is a number of control points, |E| is a number of pairs of neighboring control points on a neighborhood system, t is an iteration counter, and associating the MRF with a primary linear program and solving the primary linear program using a fast primal-dual algorithm to yield a coordinate transformation that minimizes the energy functional.

System and method for dense image registration using Markov Random Fields and efficient linear programming

Growing community of inventors

Munich, Germany

Benjamin Glocker