DocumentCode
2993951
Title
Using perceptual grouping to recognize and locate partially occluded objects
Author
Rearick, T.C. ; Frawley, J.L. ; Cortopassi, P.P.
Author_Institution
Lockheed Aeronaut. Syst. Co., Marietta, GA, USA
fYear
1988
fDate
5-9 Jun 1988
Firstpage
840
Lastpage
846
Abstract
The authors describe a connectionist network which is not a neural net in which knowledge is distributed globally via the connections of functionally simple nodes. The technique combines constraint propagation with analogical or eidetic representations. It represents an alternative to the atomistic signals-to-symbols paradigm in which a one-to-one correspondence is assumed to exist between symbols and the concepts they represent
Keywords
artificial intelligence; knowledge engineering; pattern recognition; visual perception; artificial intelligence; connectionist network; constraint propagation; eidetic representations; knowledge engineering; partially occluded objects; pattern recognition; perceptual grouping; Computational modeling; Image recognition; Layout; Machine intelligence; Machine vision; Neural networks; Prototypes; Shape; Spatial resolution; Testing;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer Vision and Pattern Recognition, 1988. Proceedings CVPR '88., Computer Society Conference on
Conference_Location
Ann Arbor, MI
ISSN
1063-6919
Print_ISBN
0-8186-0862-5
Type
conf
DOI
10.1109/CVPR.1988.196331
Filename
196331
Link To Document