Foundations Of Cognitive Science

Visual Routines

Ullman (1984) noted that the perception of spatial relations is central to visual processing.  However, many spatial relations cannot be directly delivered by the parallel, data-driven processes postulated by natural computationalists.  This is because these relations are not defined over entire scenes, but are instead defined over particular entities in scenes (i.e. objects or their parts).  Furthermore, many of these relations must be computed using serial processing of the sort that is not proposed to be part of the networks that propagate natural constraints. With such considerations in mind, Ullman (1984, 2000) developed a theory of visual routines.  In an initial stage of processing, data-driven processes deliver representations of the visual scene.  In the second stage, visual cognition executes visual routines at specified locations in the representations delivered by the first stage of processing. Visual routines are built from a set of elemental operations, and are used to establish spatial relations and shape properties.  Candidate elemental operations include indexing a salient item, spreading activation over a region, and tracing boundaries.  A visual routine is thus a program, assembled out of elemental operations, which is activated when needed to compute a necessary spatial property.  Visual routines are part of visual cognition because attention is used to select a necessary routine (and possibly create a new one), and to direct the routine to a specific location of interest.  However, once the routine is activated, it can deliver its spatial judgment without requiring additional higher-order resources.  “Visual routines operate in the middle ground that, unlike the bottom-up creation of the base representations, is a part of the top-down processing and yet is independent of object-specific knowledge. Their study therefore has the advantage of going beyond the base representations while avoiding many of the additional complications associated with higher level components of the system (Ullman, 1984, p. 119).


  1. Ullman, S. (1984). Visual routines. Cognition, 18, 97-159.
  2. Ullman, S. (2000). High-Level Vision: Object Recognition And Visual Cognition. Cambridge, Mass.: MIT Press.

(Added March 2011)