This paper presents a kernel method that allows to combine color and shape information for appearance-based object recognition. It doesn't require to define a new common representation, but use the power of kernels to combine different representations together in an effective manner. These results are achieved using results of statistical mechanics of spin glasses combined with Markov random fields via kernel functions. Experiments show an increase in recognition rate up to 5.92% with respect to conventional strategies.
How to combine color and shape information for 3D object recognition: kernels do the trick / Caputo, Barbara; Dorko, G.. - STAMPA. - (2002). (Intervento presentato al convegno 16th Annual Neural Information Processing Systems Conference tenutosi a Vancouver, BC; Canada nel 09-14 December 2002).
How to combine color and shape information for 3D object recognition: kernels do the trick
CAPUTO, BARBARA;
2002
Abstract
This paper presents a kernel method that allows to combine color and shape information for appearance-based object recognition. It doesn't require to define a new common representation, but use the power of kernels to combine different representations together in an effective manner. These results are achieved using results of statistical mechanics of spin glasses combined with Markov random fields via kernel functions. Experiments show an increase in recognition rate up to 5.92% with respect to conventional strategies.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
