A new cognitive architecture for artificial vision is proposed. The ar
chitecture, aimed at an autonomous intelligent system, is cognitive in
the sense that several cognitive hypotheses have been postulated as g
uidelines for its design. The first one is the existence of a conceptu
al representation level between the subsymbolic level, that processes
sensory data, and the linguistic level, that describes scenes by means
of a high level language, The conceptual level plays the role of the
interpretation domain for the symbols at the linguistic levels. A seco
nd cognitive hypothesis concerns the active role of a focus of attenti
on mechanism in the link between the conceptual and the linguistic lev
el: the exploration process of the perceived scene is driven by lingui
stic and associative expectations, This link is modeled as a time dela
y attractor neural network, Results are reported obtained by an experi
mental implementation of the architecture.