Q6

Structural description theories of object recognition, such as Biederman’s recognition-by-components (RBC) model, suggest that when an object is perceived, it is represented as a series of volumetric parts (e.g., geons in RBC) and the categorical relations between the parts (e.g., above, below, beside). Once an object is represented as volumetric parts and spatial relations, the process of object recognition itself is rather straightforward and invariant with viewpoint. View-based models of object recognition, on the other hand, propose that objects are represented as a collection of remembered views of the object, where views are stored as templates. Accordingly, initial representation of the object is easy, but matching the perceived view to representations in memory is difficult. Structural description models propose that object recognition is viewpoint invariant whereas view-based theories propose that object recognition should be slower for objects seen from novel viewpoints. There is much debate in the literature, but it seems that observers do not show complete viewpoint invariance in object recognition

Middle vision refers to a set of processes that combine features detected in early vision (such as edges and contours) into objects. Middle vision utilizes rules and principles for combining elements into perceptual groups, many of which were discovered by psychologists from the Gestalt tradition. Some important steps in middle vision include finding edges of objects, dealing with occlusion, texture segmentation and grouping, and determining figure/ground assignments.

Faces are different than other objects because all faces have the same parts in the same relationships with one another (e.g., eyes above nose, which is above the mouth). Therefore, fine metric details of faces are important in recognition, and it seems the visual system represents faces holistically in terms of these fine metric details, whereas it does not in the case of objects. Further evidence that the visual system treats faces and objects differently is the double dissociation between face and object recognition regions of the brain. Some patients with brain damage develop object agnosia and cannot recognize objects but can still recognize faces. Other patients develop prosopagnosia and thus cannot recognize faces but can recognize other objects. Finally, inverted faces are much harder for us to recognize than inverted objects, suggesting that faces are processed differently than objects.

The “What” pathway, also known as the ventral pathway, extends from the occipital lobe to the temporal lobe of the brain and is primarily concerned with object identity. The “Where” pathway, also known as the dorsal pathway, extends from the occipital lobe to the parietal lobe and is primarily concerned with the locations of objects in space and the actions required to interact with them.