# Recognition by Components Theory

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
34,196pages on
this wiki

The Recognition-by-components theory, or RBC theory1, is a bottom-up process proposed by Irving Biederman to explain object recognition. According to RBC theory, we are able to recognize objects by separating them into geons. Geons can be composed of various shapes (i.e. cylinders, cones, etc.) that can be assembled in various arrangements to form a virtually unlimited amount of objects.

## Strengths of the theoryEdit

Utilizing geons as structural primitives results in two key advantages. Because geons are based on object properties that are stable across viewpoint ('viewpoint invariant'), and all geons are disciminable from one another, a single geon description is sufficient to describe an object from all possible viewpoints. The second advantage is that considerable economy of representation is achieved: a relatively small set of geons form a simple "alphabet" that can combine to form complex objects. For example, with only 24 geons, there are 306 billion possible combinations of 3 geons, allowing for all possible objects to be recognised.

## Experimental evidenceEdit

• Participants show a remarkable ability to recognise objects despite visual noise provided that the geons are visible
• Removal of feature-relation information (relations between geons) impairs object recognition
• No visual priming if different geons are used between trials

## WeaknessesEdit

RBC theory is not in itself capable of starting with a photograph of a real object and producing a geons-and-relations description of the object; the theory does not attempt to provide a mechanism to reduce the complexities of real scenes to simple geon shapes. RBC theory is also incomplete in that geons and the relations between them will fail to distinguish many real objects. For example, a pear and an apple are easily distinguished by humans but lack the corners and edges needed for RBC theory to recognize they are different. However, Irving Biederman has argued that RBC theory is the "preferred" mode of human object recognition, with a secondary process handling objects that are not distinguishable by their geons. He further states that this distinction explains research suggesting that objects may or may not be recognized equally well with changes in viewpoint².

## ReferencesEdit

Sternberg, Robert J. (2006): Cognitive Psychology. 4th Ed. Thomson Wadsworth.
1Biederman, I. (1987) Recognition-by-components: a theory of human image understanding. Psychol Rev. 1987 Apr;94(2):115-47.
²Biederman, I. (2000). Recognizing depth-rotated objects: A review of recent research and theory. Spatial Vision, 13, 241-253.