A common approach to human action recognition is to use 2-D silhouettes in the space-time volume as a basis for further extraction of useful features. In this paper, we present a ...
We propose to include synchrony effects, known to exist in the auditory system, to represent voiced parts of the speech signal in a robust way. The system decomposes the input sig...
Patricia A. Pelle, Claudio Estienne, Horacio Franc...
—CENTRIST (CENsus TRansform hISTogram), a new visual descriptor for recognizing topological places or scene categories, is introduced in this paper. We show that place and scene ...
In this paper we present a symbols recognition system for graphic documents, based on a combination of global structural approaches. Our system allows to extract components and the...
Regularities in the world are human defined. Patterns in the observed phenomena are there because we define and recognize them as such. Automatic pattern recognition tries to bridg...