Title :
Learning rules for 3D object recognition
Author :
Hoffman, Richard ; Jain, Anil K.
Author_Institution :
Northrop Res. & Technol. Center, Palos Verdes Peninsula, CA, USA
Abstract :
A fully autonomous computer-vision system needs the ability to automatically learn, or discover, from training views of objects the object information (models) needed for recognition. One approach to object recognition uses an evidence rulebase composed of objects with corresponding degrees of evidence for the various objects in the databases. A technique for automatically deriving the evidence rulebase from training views of objects is presented. This generated rulebase is shown to provide successful recognition of new views of those objects
Keywords :
artificial intelligence; computer vision; learning systems; 3D object recognition; artificial intelligence; autonomous computer-vision system; evidence rulebase; learning rules; learning systems; training views; Artificial intelligence; Computer science; Computer vision; Horses; Humans; Image converters; Object recognition; Shape; Spatial databases; Training data;
Conference_Titel :
Computer Vision and Pattern Recognition, 1988. Proceedings CVPR '88., Computer Society Conference on
Conference_Location :
Ann Arbor, MI
Print_ISBN :
0-8186-0862-5
DOI :
10.1109/CVPR.1988.196337
