We discuss the relationship between the discriminative training of Gaussian models and the maximum entropy framework for log-linear models. Observing that linear transforms leave ...
MAP estimation of Gaussian mixtures through maximisation of penalised likelihoods was used to learn models of spatial context. This enabled prior beliefs about the scale, orientat...
The paper considers making inferences about the underlying true 2-D motion when only evaluations of a local block-based cost function, the mean of absolute or squared differences,...
A robust modelling method for detecting and measuring isotropic, linear features and bifurcations is described and applied to analysing 2d eletrophoresis and retinal images. Featu...
In this paper we present a probabilistic and continuous framework for supervised image category modelling and matching as well as unsupervised clustering of image space into image...