We propose a multimodal free form registration algorithm based on maximization of mutual information. Images to be aligned are modeled as a viscous fluid that deforms under the inf...
Emiliano D'Agostino, Frederik Maes, Dirk Vandermeu...
The problem of joint modeling the text and image components of multimedia documents is studied. The text component is represented as a sample from a hidden topic model, learned wi...
Nikhil Rasiwasia, Jose Costa Pereira, Emanuele Cov...
Abstract— We present a general framework for vessel segmentation in retinal images with a particular focus on small vessels. The retinal images are first processed by a nonlinea...
The paper deals with the design and implementation of a stereo algorithm. Disparity map is formulated as a Markov Random Field with a new smoothness constraint depending not only ...
Nello Balossino, Maurizio Lucenteforte, Luca Piova...
This paper presents a new approach for video clip retrieval based on Earth Mover’s Distance (EMD). Instead of imposing one-to-one matching constraint as in [11, 14], our approach...