We propose a method for reliably and accurately identifying anatomical landmarks in 3D CT volumes based on dense matching of parts-based graphical models. Such a system can be use...
We propose a registration algorithm based on successively refined quantization and an alignment metric derived from a minimal spanning tree entropy estimate. The metric favors edg...
Abstract. The goal of this paper is to present a novel recipe for deformable image registration under varying illumination, as a natural extension of the demons algorithm. This gen...
In this paper, we present an automatic classification framework combining appearance based features and Hidden Markov Models (HMM) to detect unusual events in image sequences. One...
A novel inversion technique is proposed to compute parametric maps showing the temperature, density and chemical composition of cosmic hot gas from X-ray hyper-spectral images. Th...
Mark O'Dwyer, Ela Claridge, Trevor Ponman, Somak R...