A cellular fuzzy associative memory for bidimensional pattern segmentation

Author

Carnimeo, Leonarda ; Giaquinto, Antonio

Author_Institution

Dipt. di Elettrotecnica ed Elettronica, Politecnico di Bari, Italy

fYear

2002

fDate

22-24 Jul 2002

Firstpage

430

Lastpage

435

Abstract

In this paper a cellular fuzzy associative memory containing fuzzy rules for gray image fuzzification in automatic vision systems is developed. This cellular processor is viewed as a subsystem of a CNN-based architecture, which aims to store both bidimensional patterns and the rules to process them. After establishing the fuzzy rules which define the fuzzy associative memory for image processing, a CNN behaving as a memory is synthesized to store them. A numerical example is reported to show how the synthesized cellular FAM can process bidimensional patterns for robotic navigation purposes.

Keywords

cellular neural nets; content-addressable storage; fuzzy neural nets; image recognition; image segmentation; robot vision; automatic vision systems; bidimensional pattern segmentation; cellular fuzzy associative memory; fuzzy rules; gray image fuzzification; image processing; robotic navigation; Associative memory; Cellular neural networks; Fuzzy systems; Image processing; Image segmentation; Machine vision; Navigation; Robot vision systems; Robotics and automation; Service robots;

fLanguage

English

Publisher

ieee

Conference_Titel

Cellular Neural Networks and Their Applications, 2002. (CNNA 2002). Proceedings of the 2002 7th IEEE International Workshop on

Print_ISBN

981-238-121-X

Type

conf

DOI

10.1109/CNNA.2002.1035080

Filename

1035080