Title :
Constructing perceptual categories
Author_Institution :
Dept. of Brain & Cognitive Sci., MIT, Cambridge, MA, USA
Abstract :
It is shown how a parameterization of the structure of the observed object (interpretable as the space of dimensions of generative operations which brought the object into existence) entails a lattice that enumerates all the allowable categories and subcategories for the class of object, along with an inferential preference hierarchy among them. Each model is constrained to be generic in its parameterization, so that each node in the lattice stands in for an entire class of objects that, all being parameterized the same way, can all be treated as equivalent to one another: the observed object´s natural category
Keywords :
category theory; inference mechanisms; visual perception; allowable categories; category flatland; generalisation; generative operations; generic models; inferential preference hierarchy; observed object; parameterization; Accidents; Humans; Image segmentation; Jacobian matrices; Lattices; Stability;
Conference_Titel :
Computer Vision and Pattern Recognition, 1992. Proceedings CVPR '92., 1992 IEEE Computer Society Conference on
Conference_Location :
Champaign, IL
Print_ISBN :
0-8186-2855-3
DOI :
10.1109/CVPR.1992.223268
