DocumentCode :
2839998
Title :
Computation in the higher visual cortices: map-seeking circuit theory and application to machine vision
Author :
Arathorn, David
Author_Institution :
Center for Comput. Biol., Montana State Univ., Bozeman, MT, USA
fYear :
2004
fDate :
13-15 Oct. 2004
Firstpage :
73
Lastpage :
78
Abstract :
Map-seeking circuit theory is a biologically based computational theory of vision applicable to difficult machine vision problems such as recognition of 3D objects in arbitrary poses amid distractors and clutter, as well as to non-recognition problems such as terrain interpretation. It provides a general computational mechanism for tractable discovery of correspondences in massive transformation spaces by exploiting an ordering property of superpositions. The latter allows a set of transformations of an input image to be formed into a sequence of superpositions which are then "culled" to a composition of single mappings by a competitive process which matches each superposition against a superposition of inverse transformations of memory patterns. The architecture that performs this is based on a number of neuroanatomical features of the visual cortices, including reciprocal dataflows and inverse mappings.
Keywords :
biology computing; computer vision; 3D object recognition; inverse mappings; inverse transformations; machine vision; map-seeking circuit theory; massive transformation spaces; memory patterns; neuroanatomical features; reciprocal dataflows; terrain interpretation; vision computational theory; visual cortices; Biology computing; Circuit theory; Computational biology; Computational intelligence; Computer architecture; Computer vision; Equations; Machine vision; Pattern matching; Psychology;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Information Theory, 2004. ISIT 2004. Proceedings. International Symposium on
ISSN :
1550-5219
Print_ISBN :
0-7695-2250-5
Type :
conf
DOI :
10.1109/AIPR.2004.20
Filename :
1409678
Link To Document :
بازگشت