Trying to compare robot vision architectures to a mythic reference like the human system might appear somewhat ambitious and asks for precautions. First two major difficulties are outlined. Drawing analogies between systems from their outputs is risky: such a limit is illustrated through one formalizing example. So, better compare major features. But a zoology of vision machines is questioned when, aiming to a well informed architectural feature choice, a rapid presentation of trends in the field is proposed.Then an approach closer to physics prompts to a classification from a control point of view: it reveals some duality between operations and communications.A few visual operations are distinguished provided technology is not trailing behind. But a fair stress must be put on communication networks if properties likely suitable for comparison are to be found.