TY - GEN
T1 - A stable graph-based representation for object recognition through high-order matching
AU - Albarelli, A.
AU - Bergamasco, F.
AU - Rossi, L.
AU - Vascon, S.
AU - Torsello, A.
PY - 2012/11
Y1 - 2012/11
N2 - Many Object recognition techniques perform some flavour of point pattern matching between a model and a scene. Such points are usually selected through a feature detection algorithm that is robust to a class of image transformations and a suitable descriptor is computed over them in order to get a reliable matching. Moreover, some approaches take an additional step by casting the correspondence problem into a matching between graphs defined over feature points. The motivation is that the relational model would add more discriminative power, however the overall effectiveness strongly depends on the ability to build a graph that is stable with respect to both changes in the object appearance and spatial distribution of interest points. In fact, widely used graph-based representations, have shown to suffer some limitations, especially with respect to changes in the Euclidean organization of the feature points. In this paper we introduce a technique to build relational structures over corner points that does not depend on the spatial distribution of the features.
AB - Many Object recognition techniques perform some flavour of point pattern matching between a model and a scene. Such points are usually selected through a feature detection algorithm that is robust to a class of image transformations and a suitable descriptor is computed over them in order to get a reliable matching. Moreover, some approaches take an additional step by casting the correspondence problem into a matching between graphs defined over feature points. The motivation is that the relational model would add more discriminative power, however the overall effectiveness strongly depends on the ability to build a graph that is stable with respect to both changes in the object appearance and spatial distribution of interest points. In fact, widely used graph-based representations, have shown to suffer some limitations, especially with respect to changes in the Euclidean organization of the feature points. In this paper we introduce a technique to build relational structures over corner points that does not depend on the spatial distribution of the features.
UR - http://www.scopus.com/inward/record.url?scp=84874557230&partnerID=8YFLogxK
M3 - Conference article published in proceeding or book
AN - SCOPUS:84874557230
SN - 9784990644109
T3 - Proceedings - International Conference on Pattern Recognition
SP - 3341
EP - 3344
BT - ICPR 2012 - 21st International Conference on Pattern Recognition
T2 - 21st International Conference on Pattern Recognition, ICPR 2012
Y2 - 11 November 2012 through 15 November 2012
ER -