Premium
The differences between Cellular Neural Network based and Fuzzy Cellular Nneural Network based mathematical morphological operations
Author(s) -
Yang Tao,
Yang ChunMei,
Yang LinBao
Publication year - 1998
Publication title -
international journal of circuit theory and applications
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.364
H-Index - 52
eISSN - 1097-007X
pISSN - 0098-9886
DOI - 10.1002/(sici)1097-007x(199801/02)26:1<13::aid-cta3>3.0.co;2-p
Subject(s) - dilation (metric space) , mathematical morphology , grey scale , cellular neural network , computer science , artificial intelligence , fuzzy logic , artificial neural network , scale (ratio) , pattern recognition (psychology) , mathematics , image processing , image (mathematics) , geometry , physics , quantum mechanics
In this paper, the differences between cellular neural network (CNN)‐based and fuzzy CNN (FCNN)‐based grey‐scale mathematical morphological operations are presented. The performances of the CNN‐based mathematical morphological operations are analyzed. The stability and the basin of attraction of conventional CNN‐based grey‐scale erosion and grey‐scale dilation are studied. We find that the conventional CNN‐based grey‐scale erosion and grey‐scale dilation can introduce some time varying and ‘random’ errors in their outputs. For comparison, the performances of the FCNN‐based grey‐scale mathematical morphological operations are also presented. We find that the FCNN‐based erosion and dilation can give error‐free results. Simulation results are given. © 1998 John Wiley & Sons, Ltd.