# Object Recognition **Keywords:** object recognition, view-based model, structural description, visual attention, viewpoint invariance **Abstract:** The dominant approaches to theorizing about and modeling human object recognition are the view-based approach, which holds that we mentally represent objects in terms of the (typically 2-dimensional; 2-D) coordinates of their visible 2-D features, and the structural description 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. **Authors:** [[John E. Hummel]]