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 :
بازگشت