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...
We propose a novel statistical manifold modeling approach that is capable of classifying poses of object categories from video sequences by simultaneously minimizing the intra-cla...
Liang Mei, Jingen Liu, Alfred Hero, Silvio Savares...
Abstract. We propose a generative approach to the problem of labeling images containing configurations of objects from multiple classes. The main building blocks are dense statisti...
Abstract--Discrete-input two-dimensional (2-D) Gaussian channels with memory represent an important class of systems, which appears extensively in communications and storage. In sp...
Ori Shental, Noam Shental, Shlomo Shamai, Ido Kant...
An approach to the deformable registration of three-dimensional brain tumor images to a normal brain atlas is presented. The approach involves the integration of three components:...