Artículos de revistas
A network of integrate and fire neurons for visual selection
Fecha
2009Registro en:
NEUROCOMPUTING, v.72, n.10, p.2198-2208, 2009
0925-2312
10.1016/j.neucom.2008.10.024
Autor
Quiles, Marcos Gonçalves
Liang, Zhao
Breve, Fabricio Aparecido
Romero, Roseli Aparecida Francelin
Institución
Resumen
Biological systems have facility to capture salient object(s) in a given scene, but it is still a difficult task to be accomplished by artificial vision systems. In this paper a visual selection mechanism based on the integrate and fire neural network is proposed. The model not only can discriminate objects in a given visual scene, but also can deliver focus of attention to the salient object. Moreover, it processes a combination of relevant features of an input scene, such as intensity, color, orientation, and the contrast of them. In comparison to other visual selection approaches, this model presents several interesting features. It is able to capture attention of objects in complex forms, including those linearly nonseparable. Moreover, computer simulations show that the model produces results similar to those observed in natural vision systems.