Inferring both 3D structure and motion of nonrigid objects from monocular images is an important problem in computational vision. The challenges stem not only from the absence of ...
Abstract. We describe a flexible object recognition and modelling system (FORMS) which represents and recognizes animate objects from their silhouettes. This consists of a model fo...
We propose a new fast facial-feature extraction technique for embedded face-recognition applications. A deformable feature model is adopted, of which the parameters are optimized t...
A model for the dynamic simulation of flexible bodies subject to non-penetration constraints is presented. Flexible bodies are described in terms of global deformations of a rest ...
This paper proposes a novel graph matching algorithm and applies it to shape recognition based on object silhouettes. The main idea is to match skeleton graphs by comparing the geo...