Geometric Hashing is a well-known technique for object recognition. This paper proposes a novel method aimed at improving the performance of Geometric Hashing in terms of robustness toward occlusion and clutter. To this purpose, it employs feature descriptors to notably decrease the amount of false positives that generally arise under these conditions. An additional advantage of the proposed technique with respect to the original method is the reduction of the computation requirements, which becomes significant with increasing number of features.
F. Tombari, L. Di Stefano (2011). Improving Geometric Hashing by means of feature descriptors. s.l. : SciTePress – Science and Technology Publications.
Improving Geometric Hashing by means of feature descriptors
TOMBARI, FEDERICO;DI STEFANO, LUIGI
2011
Abstract
Geometric Hashing is a well-known technique for object recognition. This paper proposes a novel method aimed at improving the performance of Geometric Hashing in terms of robustness toward occlusion and clutter. To this purpose, it employs feature descriptors to notably decrease the amount of false positives that generally arise under these conditions. An additional advantage of the proposed technique with respect to the original method is the reduction of the computation requirements, which becomes significant with increasing number of features.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.