A homogeneous paradigm for evidence integration is presented, and a vision system to recognize 3D objects is demonstrated using this paradigm. A new concept called generalizedfeat...
Rick Kjeldsen, Ruud M. Bolle, Andrea Califano, Rus...
Many modern visual recognition algorithms incorporate a step of spatial `pooling', where the outputs of several nearby feature detectors are combined into a local or global `...
We propose a joint representation and classification framework that achieves the dual goal of finding the most discriminative sparse overcomplete encoding and optimal classifier p...
In this paper, we integrate type-2 (T2) fuzzy sets with Markov random fields (MRFs) referred to as T2 FMRFs, which may handle both fuzziness and randomness in the structural patter...
Recognizing faces in unconstrained videos is a task of mounting importance. While obviously related to face recognition in still images, it has its own unique characteristics and ...