A framework for high-level representations in computer vision architectures
is described. The framework is based on the notion of conceptual space. Th
is approach allows us to define a conceptual semantics for the symbolic rep
resentations of the vision system. In this way, the semantics of the symbol
s can be grounded to the data coming from the sensors. In addition, the pro
posed approach generalizes the most popular frameworks adopted in computer
vision.