Cellular neural network design for solving specific image-processing problems

This paper is concerned with determining simple CNN-paradigm-based circuits for solving specific binary image-processing problems. Single-layer CNN templates for performing specified shape extraction, extraction of shapes which contain a desired feature and modified feature detection are derived using a formulated design strategy. the concept of CNNs composed of modified cells is developed and circuits designed for realizing simultaneous detection of distinct features and for extracting horizontal line midpoints are presented.

[1]  Kari Halonen,et al.  VLSI implementation of a reconfigurable cellular neural network containing local logic (CNNL) , 1990, IEEE International Workshop on Cellular Neural Networks and their Applications.

[2]  K. Slot,et al.  Determination of cellular neural networks parameters for feature detection of two-dimensional images , 1990, IEEE International Workshop on Cellular Neural Networks and their Applications.

[3]  Tamás Roska,et al.  Cellular neural networks with nonlinear and delay-type template elements , 1990, IEEE International Workshop on Cellular Neural Networks and their Applications.

[4]  Lin-Bao Yang,et al.  Cellular neural networks: theory , 1988 .

[5]  Josef A. Nossek,et al.  Cellular neural network design using a learning algorithm , 1990, IEEE International Workshop on Cellular Neural Networks and their Applications.

[6]  Leon O. Chua,et al.  Cellular neural networks: applications , 1988 .

[7]  Leon O. Chua,et al.  Several image processing examples by CNN , 1990, IEEE International Workshop on Cellular Neural Networks and their Applications.