DocumentCode :
296170
Title :
Enhanced Hopfield network for morphologic image processing
Author :
Lu, Si Wei ; Ghica, Dan
Author_Institution :
Memorial Univ. of Newfoundland, St. John´´s, Nfld., Canada
Volume :
4
fYear :
1995
fDate :
Nov/Dec 1995
Firstpage :
2091
Abstract :
Hopfield networks are neural architectures remarkable by architectural simplicity and flexibility in usage. There are many areas in which Hopfield networks have been successfully applied, including associative memories, pattern recognition and artificial intelligence. This paper proposes a novel application of Hopfield networks in image processing, as morphologic filters, and illustrates the concept with a comprehensive example of a morphologic filter used for feature extraction
Keywords :
Hopfield neural nets; edge detection; feature extraction; filtering theory; mathematical morphology; architectural simplicity; associative memories; enhanced Hopfield network; feature extraction; flexibility; morphologic filters; morphologic image processing; neural architectures; pattern recognition; Artificial intelligence; Associative memory; Computer architecture; Computer networks; Concurrent computing; Feature extraction; Filters; Image processing; Parallel processing; Pattern recognition;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1995. Proceedings., IEEE International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-2768-3
Type :
conf
DOI :
10.1109/ICNN.1995.488998
Filename :
488998
Link To Document :
بازگشت