ABSTRACT
Vision allows organisms to know the contents and layout of their local environment. Its major function is object recognition. Experimental evi dence accumulated over the last 30 years suggests that in many (but not all) cases, the visual system accomplishes object recognition by visually selecting a relevant or salient part of the visual image (e.g. the cluster of features constituting an object or located in a region of space) and operating only on that cluster, then selecting another part of the image, and so forth. This strategy reduces the complexity of object recognition by limiting it to only one or a small number of elements at a time. The mechanism that accom plishes selection is called visual attention, and this chapter is concerned with how visual attention is deployed within an image as a function of image properties and observer goals.
