Symbol spotting problem requires feature extraction strategies able to generalize from training samples and to localize the target object while discarding most part of the image. ...
Previous Multiple Kernel Learning approaches (MKL) employ different kernels by their linear combination. Though some improvements have been achieved over methods using single kerne...
In this contribution we focus on the calibration of very long image sequences from a hand-held camera that samples the viewing sphere of a scene. View sphere sampling is important...
Reinhard Koch, Marc Pollefeys, Benno Heigl, Luc J....
: A Burg technique is employed to model the long wavelength localization and imaging problem. A Burg method is used as a high resolution and stable technique. The idea of in-line h...
In this paper we propose and evaluate an algorithm that learns a similarity measure for comparing never seen objects. The measure is learned from pairs of training images labeled ...