For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Synthesis of Discrete-Time Cellular Neural Networks for Binary Image Processing
Chun-Ying HO Dao-Heng Yu Shinsaku MORI
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 1993/05/25
Print ISSN: 0916-8508
Type of Manuscript: Special Section PAPER (Special Section on Neural Nets,Chaos and Numerics)
Category: Neural Nets--Theory and Applications--
synthesizing approach, threshold function, threshold logic, Boolean function, l-realizabilty, sensitivity, direct-R realization,
Full Text: PDF>>
In this paper, a synthesizing method is proposed for the design of discrete-time cellular neural networks for binary image processing. Based on the theory of digital-logical design paradigm of threshold logic, the template parameters of the discrete-time cellular neural network for a prescribed binary image processing problem are calculated. Application examples including edge detection, connected component detection, and hole filling are given to demonstrate the merits and limitations of the proposed method. For a given realization of the parameters of the cloning template, a guideline for the selection of the offset Ic for maximum error tolerance is also considered.