High-performance and low-power VLIW DSP processors are increasingly deployed on embedded devices to process video and multimedia applications. For reducing power and cost in desig...
The low-rank matrix approximation problem involves finding of a rank k version of a m ? n matrix AAA, labeled AAAk, such that AAAk is as "close" as possible to the best ...
A linear programming technique is introduced that jointly performs feature selection and classifier training so that a subset of features is optimally selected together with the c...
Feature points for image correspondence are often selected according to subjective criteria (e.g. edge density, nostrils). In this paper, we present a general, non-subjective crit...
Existing sequential feature-based registration algorithms involving search typically either select features randomly (eg. the RANSAC[8] approach) or assume a predefined, intuitive...