In this paper, a generic bi-directional framework is proposed for parametric image alignment, that extends the classification of [1]. Four main categories (Forward, Inverse, Depend...
We propose a feature selection method that constructs each new feature by analysis of tight error clusters. This is a greedy, time-efficient forward selection algorithm that itera...
In this paper, we present a new model-based approach for building 3-D models of vehicles from color video provided by a traffic surveillance camera. We incrementally build 3D mode...
We present in this paper a new multi-class Bayes classifier that permits using separate feature vectors, chosen specifically for each class. This technique extends previous work o...
We report on a new framework to investigate the rapid brain development of newborns. It is based on the analysis of depth maps of the cortical surface through the study of a displa...