The paper presents a non parametric image registration method based on an explicit representation of the warping function. The image registration problem is approached in the Bayesian framework with a prior term given by a Gaussian random field accounting the regularity of a deformable grid. The observation term is accounted with two terms in the energy functional, the first depends on the quality of recontruction of the target image with respect the source image, the second is based on a set of landmarks automatically detected between the images to be registered. The algorithm is completely unsupervised, making it suitable for high throughput biomedical applications such as proteomics and cellular imaging
Bayesian grid matching for 2D gel registration
Ceccarelli M;
2010-01-01
Abstract
The paper presents a non parametric image registration method based on an explicit representation of the warping function. The image registration problem is approached in the Bayesian framework with a prior term given by a Gaussian random field accounting the regularity of a deformable grid. The observation term is accounted with two terms in the energy functional, the first depends on the quality of recontruction of the target image with respect the source image, the second is based on a set of landmarks automatically detected between the images to be registered. The algorithm is completely unsupervised, making it suitable for high throughput biomedical applications such as proteomics and cellular imagingI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.