Abstract and Keywords
The dominant approaches to theorizing about and modeling human object recognition are the approach, which holds that we mentally represent objects in terms of the (typically two-dimensional [2D]) coordinates of their visible 2D features, and the approach, which holds that we represent objects in terms of the (typically categorical) spatial relations among their (typically volumetric) parts. This chapter reviews the history and nature of these (and other) models of object recognition, as well as some of the empirical evidence for and against each of them. I will argue that neither account is adequate to explain the full range of empirical data on human object recognition and conclude by suggesting that the visual system uses an intelligent combination of structure- and view-based approaches.
Access to the complete content on Oxford Handbooks Online requires a subscription or purchase. Public users are able to search the site and view the abstracts and keywords for each book and chapter without a subscription.
If you have purchased a print title that contains an access token, please see the token for information about how to register your code.