F. Brunet, A. Bartoli, J. Peyras, N. Navab, R. Malgouyres Découverte automatique de la région d'intérêt en recalage d'images direct Actes du onzième congrès francophone des jeunes chercheurs en vision par ordinateur, Trégastel, Juin 2009 (bib)
	The goal of the direct aggregative image registration problem is to aggregate in an incremental way a set of images by minimizing the pixel intensity discrepancy between the current aggregate and each new image. One of the bigest drawback of this method is that it relies on an a priori knowledge of the overlapping area (or region of interest) between the aggregate and the new image. In practice, the region of interest is specified by the user. In this article, we propose and compare several new approaches for which an a priori knowledge of the region of interest is not required anymore.
	This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each authors copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.