Mirror-symmetry in images and 3D shapes
Apparaît dans la collection : Computational geometry days / Journées de géométrie algorithmique
Several psychophysical studies stress the importance of object symmetries in human perception when dealing with tasks related to object detection and recognition. Paradoxically, state-of-the-art methods in image and D shape analysis not only they reveal very limited use of object symmetry information, but they often regard symmetries as an issue. This talk will tackle this paradox, by addressing aspects linked to symmetry detection in images, and 3D shape matching in presence of symmetries. Specifically, a method for reducing the umber of false positives in symmetry detection in images will be presented, as well as a 3D shape matching approach that solves the ambiguity induced by intrinsic symmetries in the shape matching problem.