Abstract--In a distributed speech recognition (DSR) framework, the speech features are quantized and compressed at the client and recognized at the server. However, recognition acc...
Efficient methods of content characterization for the browsing, retrieval or filtering of vast amount of digital video content has become a necessity. Still, there is a gap betwee...
A robust modelling method for detecting and measuring isotropic, linear features and bifurcations is described and applied to analysing 2d eletrophoresis and retinal images. Featu...
A novel scheme for the detection of object boundaries is presented. The technique is based on active contours evolving in time according to intrinsic geometric measures of the imag...
We present a new and efficient semi-supervised training method for parameter estimation and feature selection in conditional random fields (CRFs). In real-world applications suc...