interpretation. We focus the discussion of the problem mainly on the 3D Morphable Model (3DMM) [2] but in principle, our results apply to different generative models. We present an analysis of the prob-lem within the probabilistic interpretation of the 3DMM fitting ⇑ Corresponding author.

It has been shown that the linear combination of prototypical views provides a powerful approach for the recognition and the synthesis of images of stationary three-dimensional objects. In this article, we present initial results that demonstrate that similar ideas can be developed for the recognition and synthesis of complex motion patterns. We present a technique that permits to represent complex motion or action patterns by linear combinations of a small number of prototypical image sequences. We demonstrate the applicability of this new approach for the synthesis and analysis of biological motion using simulated and real video data from dierent locomotion patterns. Our results show that complex motion patterns are embedded in pattern spaces with a de ned topological structure, which can be uncovered with our methods. The underlying pattern space seems to have locally, but not globally, the properties of a linear vector space. It is shown how the knowledge about the topology of the pattern space can be exploited during pattern recognition. Our method may provide a new interesting approach for the analysis and synthesis of video sequences and complex movements.

In this paper, a new technique for modeling textured 3D faces is introduced. 3D faces can either be generated automatically from one or more photographs, or modeled directly through an intuitive user interface. Users are assisted in two key problems of computer aided face modeling. First, new face

We describe a flexible model for representing images of objects of a certain class, known a priori, such as faces, and introduce a new algorithm for matching it to a novel image and thereby performing image analysis. We call this model a multidimensional morphable model or just a morphable model

formation in 3D space, using computer graphics, and it estimates 3D shape and texture of faces from single images. The estimate is achieved by fitting a statistical, morphable model of 3D faces to images. The model is learned from a set of textured 3D scans of heads. We describe the construction

Statistical shape and texture appearance models are powerful image representations, but previously had been restricted to 2D or simple 3D shapes. In this paper we present a novel 3D morphable model based on image-based rendering techniques, which can represent complex lighting conditions

one example image per person is available for training. To tackle this problem, Fisherface method is extended by utilizing 3D morphable model to derive multiple images of a face from one single image. Experimental results on ORL face database and real time face database show that face recognition

Full metadata for this item is available in the St Andrews

Heliox improves pulmonary mechanics in a pediatric porcine

■ Automated face recognition performance suffers when conditions for facial image capture are not constrained. – FRVT 2002 Evaluation [1] – Median rank-1 identification rate 0.19 at 45o left/right rotation – Median rank-1 identification rate 0.34 at 30o up/down rotation – FRGC Evaluation [2] – Median verification rate 0.91 with controlled illumination – Median verification rate 0.42 with uncontrolled illumination